INDEX

Explanations

specific political terms and names

oai_token-act-pair · gpt-3.5-turbo

phrases indicating unfairness or bias in political contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

pmwiki

-0.94

ItemTracker

-0.80

âĹ¼

-0.76

adobe

-0.69

anse

-0.67

ansk

-0.65

endum

-0.64

byss

-0.64

addons

-0.62

nce

-0.62

POSITIVE LOGITS

 Dems

0.87

 Pelosi

0.83

 Kavanaugh

0.81

DNC

0.77

 Biden

0.76

 Democrats

0.76

 Democratic

0.75

 Democrat

0.74

 Democr

0.73

GOP

0.73

Activations Density 0.056%

specific political terms and names

phrases indicating unfairness or bias in political contexts

No Comments

No Known Activations