INDEX

Explanations

colors and color-related words

oai_token-act-pair · gpt-3.5-turbo

references to colors

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

doms

-0.99

_-

-0.94

idem

-0.90

=-=-=-=-

-0.74

llah

-0.74

rican

-0.73

uthor

-0.69

 ARTICLE

-0.68

ICLE

-0.68

ickson

-0.68

POSITIVE LOGITS

 palette

1.19

 colors

1.10

 colours

1.04

 color

0.98

color

0.95

dye

0.94

anguage

0.93

 tint

0.93

colour

0.92

pace

0.89

Activations Density 0.019%

colors and color-related words

references to colors

No Comments

No Known Activations