INDEX

Explanations

phrases related to intense actions or emotional states

oai_token-act-pair · gpt-3.5-turbo

forms of the verb "to be" in various conjugations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Luther

-0.78

 Cosponsors

-0.70

rition

-0.69

enegger

-0.68

 Annotations

-0.64

FD

-0.63

 Holocaust

-0.63

ropolitan

-0.62

 Feld

-0.61

NEY

-0.61

POSITIVE LOGITS

veland

1.16

wa

0.99

vel

0.97

iving

0.94

aaa

0.94

aaaa

0.93

ver

0.92

ccess

0.91

ike

0.90

isted

0.88

Activations Density 0.016%

phrases related to intense actions or emotional states

forms of the verb "to be" in various conjugations

No Comments

No Known Activations