INDEX

Explanations

responses to questions or statements

oai_token-act-pair · gpt-3.5-turbo

instances of dialogue, specifically replies or responses in conversations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

teenth

-0.75

mental

-0.72

fi

-0.69

ctors

-0.66

BALL

-0.66

icipated

-0.66

dar

-0.64

flame

-0.64

 Trials

-0.63

cipled

-0.63

POSITIVE LOGITS

 thereto

0.98

 angrily

0.85

 favorably

0.85

 sarcast

0.84

 affirm

0.84

 promptly

0.80

 politely

0.79

reply

0.78

 enthusiastically

0.77

later

0.75

Activations Density 0.038%

responses to questions or statements

instances of dialogue, specifically replies or responses in conversations

No Comments

No Known Activations