INDEX

Explanations

proper nouns related to individuals

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals and mentions of spam

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GA

-0.73

 heats

-0.70

erness

-0.70

erm

-0.69

pill

-0.67

 provision

-0.66

 HTTP

-0.65

basketball

-0.64

HTTP

-0.64

road

-0.63

POSITIVE LOGITS

 Schneider

1.81

 Vincent

1.54

 Viktor

1.34

 Echo

1.34

 Sven

1.21

 Spect

1.20

 spam

1.18

 Pierre

1.08

Spect

1.02

 Cousins

1.01

Activations Density 0.029%

proper nouns related to individuals

references to specific individuals and mentions of spam

No Comments

No Known Activations