INDEX

Explanations

mentions of politicians with the title of "congressman" followed by their names

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "congressman."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

phal

-0.88

istically

-0.85

istic

-0.79

condition

-0.72

kus

-0.70

 paras

-0.70

word

-0.70

zees

-0.70

 Dragonbound

-0.69

ologically

-0.67

POSITIVE LOGITS

 Congressman

0.89

 congressman

0.89

 Issa

0.83

Ike

0.82

 Franch

0.79

ublic

0.73

 Nixon

0.71

 Lyndon

0.71

å°Ĩ

0.70

resents

0.70

Activations Density 0.026%

mentions of politicians with the title of "congressman" followed by their names

mentions of the term "congressman."

No Comments

No Known Activations