INDEX

Explanations

mentions of specific political figures, particularly Obama and Trump, along with policy-related terms

oai_token-act-pair · gpt-3.5-turbo

mentions of political figures, particularly Obama and Trump

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

NetMessage

-0.84

abwe

-0.80

terday

-0.79

-0.73

duty

-0.70

govtrack

-0.70

hemy

-0.70

verbs

-0.70

alam

-0.68

*/(

-0.68

POSITIVE LOGITS

 administration

1.08

 presidency

0.95

 playbook

0.90

 campaign

0.88

 Administration

0.86

era

0.85

 agenda

0.83

 umbrella

0.81

 electorate

0.80

 academy

0.78

Activations Density 0.144%

mentions of specific political figures, particularly Obama and Trump, along with policy-related terms

mentions of political figures, particularly Obama and Trump

No Comments

No Known Activations