INDEX

Explanations

specific words related to a "pub"

oai_token-act-pair · gpt-3.5-turbo

references to pubs

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

OHN

-0.80

llor

-0.75

IRD

-0.72

 Marketable

-0.72

 Gaia

-0.72

ioxide

-0.69

 GOODMAN

-0.66

 Archangel

-0.66

 Reson

-0.66

EFF

-0.65

POSITIVE LOGITS

lique

1.35

lishes

1.33

lish

1.26

lisher

1.22

escent

1.21

lishing

1.20

bing

0.98

lik

0.97

 crawl

0.91

ishes

0.90

Activations Density 0.014%

specific words related to a "pub"

references to pubs

No Comments

No Known Activations