INDEX

Explanations

phrases related to stating and emphasizing different points or facts

oai_token-act-pair · gpt-3.5-turbo

statements about notable events or changes in organizations or situations

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

pedia

-0.72

hol

-0.68

iasm

-0.60

hs

-0.58

osate

-0.56

ossom

-0.56

 Removal

-0.55

 congr

-0.54

Hello

-0.54

urry

-0.54

POSITIVE LOGITS

 remarkably

0.96

 exceedingly

0.95

 extraordinarily

0.93

 exceptionally

0.89

 VERY

0.87

 actually

0.86

 extremely

0.85

 incredibly

0.83

 decidedly

0.82

 disproportionately

0.81

Activations Density 0.749%

phrases related to stating and emphasizing different points or facts

statements about notable events or changes in organizations or situations

No Comments

No Known Activations