INDEX

Explanations

references to the United States or related terms

oai_token-act-pair · gpt-3.5-turbo

mentions of the United States and its government

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Emin

-0.79

quickShipAvailable

-0.76

hots

-0.71

 nick

-0.71

INTER

-0.69

 Razer

-0.69

LOD

-0.66

 evict

-0.66

Sak

-0.64

 blur

-0.64

POSITIVE LOGITS

 Constitution

1.05

 economy

1.04

 Accountability

0.88

 Economy

0.84

 constitution

0.84

 democracy

0.82

 Citizenship

0.82

 workforce

0.81

 electorate

0.81

wide

0.80

Activations Density 0.220%

references to the United States or related terms

mentions of the United States and its government

No Comments

No Known Activations