INDEX

Explanations

terms related to financial health and social welfare, particularly focusing on subsidies, taxes, and income levels of Americans

oai_token-act-pair · gpt-3.5-turbo

references to low-income populations and their needs

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rontal

-0.71

Reloaded

-0.69

yss

-0.67

PDATE

-0.66

rawdownloadcloneembedreportprint

-0.66

awa

-0.64

WIND

-0.62

ASED

-0.60

cknowled

-0.60

ModLoader

-0.59

POSITIVE LOGITS

hip

0.89

hips

0.88

 alike

0.83

paces

0.75

who

0.70

riages

0.68

folk

0.68

(<

0.67

lings

0.66

ervatives

0.65

Activations Density 0.371%

terms related to financial health and social welfare, particularly focusing on subsidies, taxes, and income levels of Americans

references to low-income populations and their needs

No Comments

No Known Activations