INDEX

Explanations

dialogue actions and inquiries within a conversation

oai_token-act-pair · gpt-3.5-turbo

dialogue and questions in conversations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

artifacts

-0.97

theless

-0.87

icultural

-0.81

rats

-0.78

etheless

-0.77

HCR

-0.76

wcs

-0.76

earable

-0.75

creation

-0.73

icter

-0.73

POSITIVE LOGITS

 sounding

0.91

 whispered

0.89

 whisper

0.88

 loudly

0.83

 aloud

0.82

 loud

0.82

 sarcast

0.82

 softly

0.81

 louder

0.79

 yelled

0.78

Activations Density 0.197%

dialogue actions and inquiries within a conversation

dialogue and questions in conversations

No Comments

No Known Activations