INDEX

Explanations

words related to political or controversial topics

oai_token-act-pair · gpt-3.5-turbo

instances of the character 'Ļ' in the text

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

 sacrific

-0.76

 hurd

-0.69

 Tanz

-0.67

 Assy

-0.67

 loopholes

-0.65

 Allied

-0.63

 mathemat

-0.63

 vulner

-0.63

 handic

-0.62

 demoral

-0.62

POSITIVE LOGITS

ï¸ı

1.12

shall

1.09

ï¸

0.97

tracks

0.94

ski

0.91

sure

0.89

ship

0.89

right

0.89

ser

0.86

Activations Density 0.251%

words related to political or controversial topics

instances of the character 'Ļ' in the text

No Comments

No Known Activations