INDEX

Explanations

terms related to political topics

oai_token-act-pair · gpt-3.5-turbo

references to politics and political issues

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

uran

-0.90

actory

-0.88

imates

-0.80

ibles

-0.79

amination

-0.78

val

-0.75

reek

-0.74

orage

-0.74

eret

-0.71

gur

-0.69

POSITIVE LOGITS

 correctness

1.02

eering

0.92

manship

0.85

hare

0.81

cape

0.81

atism

0.77

 governing

0.76

 lawy

0.76

clinton

0.75

 intrig

0.74

Activations Density 0.018%

terms related to political topics

references to politics and political issues

No Comments

No Known Activations