INDEX

Explanations

locations or geographic regions

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of locations and people

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

dress

-0.86

uit

-0.84

hog

-0.74

bed

-0.74

kick

-0.73

uckland

-0.73

oor

-0.71

ishly

-0.68

draw

-0.68

hart

-0.68

POSITIVE LOGITS

sylvania

0.81

arest

0.80

illin

0.74

Sut

0.72

Ð´

0.72

FUL

0.70

ivable

0.69

onductor

0.69

 Takeru

0.65

 constitu

0.64

Activations Density 0.064%

locations or geographic regions

proper nouns, particularly names of locations and people

No Comments

No Known Activations