INDEX

Explanations

words related to attributing blame or responsibility

oai_token-act-pair · gpt-3.5-turbo

instances of the word "blame" and its variations 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 @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 acquisition

-0.73

 corpus

-0.71

 length

-0.68

dra

-0.65

 Open

-0.64

 enlarg

-0.64

ples

-0.64

Num

-0.64

clus

-0.63

ongo

-0.62

POSITIVE LOGITS

 blamed

3.65

 blames

2.75

 blame

2.30

 blaming

2.26

 scapego

1.67

 attributed

1.67

 criticised

1.52

 apologized

1.52

 accused

1.52

 apologised

1.51

Activations Density 0.019%

words related to attributing blame or responsibility

instances of the word "blame" and its variations in the text

No Comments

No Known Activations