INDEX

Explanations

references to specific amounts of money in a year

oai_token-act-pair · gpt-3.5-turbo

mentions of annual income statistics

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

hod

-0.75

ibaba

-0.74

ells

-0.73

estern

-0.71

erest

-0.69

ablishment

-0.68

ativity

-0.67

assies

-0.67

ifax

-0.66

isms

-0.66

POSITIVE LOGITS

ago

0.83

Downloadha

0.79

 thereafter

0.77

Â²

0.72

 basis

0.72

 supplement

0.68

 average

0.67

/$

0.66

Lago

0.66

 metric

0.65

Activations Density 0.046%

references to specific amounts of money in a year

mentions of annual income statistics

No Comments

No Known Activations