INDEX

Explanations

phrases or sentences indicating the necessity for something or an action

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing necessity or requirements

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

 rabbit

-0.75

 Surv

-0.73

imore

-0.63

 Dice

-0.61

 Sabb

-0.61

é¾

-0.60

 dishes

-0.60

Alb

-0.59

 Halls

-0.59

dylib

-0.58

POSITIVE LOGITS

lessly

1.37

lest

0.86

kward

0.79

iness

0.78

ful

0.78

ioned

0.73

lessness

0.73

oppers

0.71

fully

0.71

onies

0.71

Activations Density 0.040%

phrases or sentences indicating the necessity for something or an action

phrases emphasizing necessity or requirements

No Comments

No Known Activations