INDEX

Explanations

mentions of political figures and election-related words

oai_token-act-pair · gpt-3.5-turbo

topics related to political commentary and analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

hens

-0.80

 Variant

-0.80

cause

-0.76

 Modified

-0.73

ocation

-0.68

Hide

-0.66

IPM

-0.65

 Join

-0.65

isable

-0.65

reads

-0.62

POSITIVE LOGITS

 already

1.05

 admittedly

0.97

 rarely

0.93

 hardly

0.90

 supposedly

0.86

 notoriously

0.81

 surely

0.80

 arguably

0.79

 previously

0.78

 practically

0.78

Activations Density 0.756%

mentions of political figures and election-related words

topics related to political commentary and analysis

No Comments

No Known Activations