INDEX

Explanations

references to locations or entities with the abbreviation "U.S."

oai_token-act-pair · gpt-3.5-turbo

references to the United States

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Noir

-0.72

 juggling

-0.68

 bars

-0.68

 remarks

-0.60

 sentences

-0.60

 stiffness

-0.59

Kaf

-0.59

 dealing

-0.57

Dj

-0.57

 moderation

-0.56

POSITIVE LOGITS

nexpected

1.23

gly

1.19

PDATED

1.12

prising

1.11

seless

1.09

mpire

1.05

LT

1.02

lyss

0.99

pperc

0.97

topia

0.96

Activations Density 0.048%

references to locations or entities with the abbreviation "U.S."

references to the United States

No Comments

No Known Activations