INDEX

Explanations

hashtags and social media activism phrases

oai_token-act-pair · gpt-3.5-turbo

mentions of social media trends and campaigns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 outset

-0.87

 substitute

-0.85

 theoretical

-0.82

 narrator

-0.80

 stem

-0.80

 attendant

-0.80

 vantage

-0.79

 range

-0.78

 compress

-0.78

 formerly

-0.78

POSITIVE LOGITS

Fail

1.60

Ban

1.59

Know

1.58

Mem

1.56

Days

1.56

Party

1.56

Years

1.54

Army

1.53

Deb

1.52

Shut

1.51

Activations Density 0.130%

hashtags and social media activism phrases

mentions of social media trends and campaigns

No Comments

No Known Activations