INDEX

Explanations

references to political figures and activities, particularly focusing on allegations or actions involving them

oai_token-act-pair · gpt-3.5-turbo

content related to investigations and evidence 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 @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 FranÃ§

-0.71

vier

-0.70

theless

-0.69

 "$:/

-0.67

mania

-0.63

ruary

-0.63

etheless

-0.62

 nonetheless

-0.60

!--

-0.60

tions

-0.58

POSITIVE LOGITS

 Kavanaugh

0.81

 Rosenstein

0.69

FBI

0.65

 Mueller

0.57

Iv

0.57

Ford

0.56

ĵ

0.54

Top

0.54

ombs

0.54

opened

0.53

Activations Density 0.029%

references to political figures and activities, particularly focusing on allegations or actions involving them

content related to investigations and evidence in political contexts

No Comments

No Known Activations