INDEX

Explanations

words related to geographical locations, specifically focusing on places like Mainland, races, upper levels, courts, and tiers

oai_token-act-pair · gpt-3.5-turbo

keywords related to social class and legal terminology

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

CVE

-0.66

CDC

-0.59

 hotline

-0.59

sand

-0.59

 Cock

-0.58

Cly

-0.58

dL

-0.57

 Garage

-0.57

 Jungle

-0.56

 Blazing

-0.55

POSITIVE LOGITS

than

1.68

 than

1.44

 Than

1.05

arsity

0.80

anguage

0.77

 wiser

0.77

uries

0.74

 installments

0.70

models

0.69

ategories

0.67

Activations Density 0.255%

words related to geographical locations, specifically focusing on places like Mainland, races, upper levels, courts, and tiers

keywords related to social class and legal terminology

No Comments

No Known Activations