INDEX

Explanations

organizations or institutions mentioned in news articles

oai_token-act-pair · gpt-3.5-turbo

instances of parentheses and organizational affiliations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 blot

-0.81

 baffled

-0.79

 impe

-0.78

lyr

-0.77

 drift

-0.76

 contempor

-0.74

 incons

-0.74

 impeachment

-0.73

 haunted

-0.73

 untreated

-0.72

POSITIVE LOGITS

formerly

1.30

aka

1.26

including

1.16

ADA

1.14

sic

1.14

UGC

1.11

which

1.06

also

1.04

SG

1.04

PDF

1.03

Activations Density 0.103%

organizations or institutions mentioned in news articles

instances of parentheses and organizational affiliations

No Comments

No Known Activations