INDEX

Explanations

comparisons between different situations or scenarios

oai_token-act-pair · gpt-3.5-turbo

comparative phrases emphasizing the notion of similarity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

hiba

-0.89

ulty

-0.86

yrinth

-0.81

iland

-0.78

bard

-0.78

iband

-0.78

acia

-0.75

iple

-0.73

icity

-0.71

ishop

-0.70

POSITIVE LOGITS

lihood

1.43

lier

1.16

liest

1.10

liness

0.88

Nor

0.78

nor

0.74

 ours

0.72

erous

0.71

able

0.70

 anything

0.70

Activations Density 0.040%

comparisons between different situations or scenarios

comparative phrases emphasizing the notion of similarity

No Comments

No Known Activations