INDEX

Explanations

words related to physical or metaphorical boundaries

oai_token-act-pair · gpt-3.5-turbo

references to boundaries and limits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ulz

-0.89

orah

-0.85

fortune

-0.81

obe

-0.78

kus

-0.76

enza

-0.75

weeney

-0.73

otos

-0.71

jury

-0.71

entanyl

-0.70

POSITIVE LOGITS

 boundaries

1.35

 boundary

1.17

 Bound

0.90

 markers

0.84

 deline

0.81

 crossings

0.79

 separating

0.79

 delim

0.77

 limits

0.75

 dividing

0.75

Activations Density 0.013%

words related to physical or metaphorical boundaries

references to boundaries and limits

No Comments

No Known Activations