INDEX

Explanations

references to the word "Grey"

oai_token-act-pair · gpt-3.5-turbo

references to the term "Grey" in a variety of contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

itia

-0.91

urity

-0.81

itu

-0.80

ATIONS

-0.78

Ì¶

-0.78

Reviewed

-0.75

ugal

-0.75

OTS

-0.75

uned

-0.74

Allah

-0.72

POSITIVE LOGITS

hound

1.44

 Grey

0.97

berry

0.95

joy

0.94

hawk

0.91

 Goose

0.88

 coloring

0.83

 wolves

0.82

Grey

0.82

burgh

0.82

Activations Density 0.003%

references to the word "Grey"

references to the term "Grey" in a variety of contexts

No Comments

No Known Activations