INDEX

Explanations

the word "two" occurring in different contexts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "two" in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ugu

-0.86

uga

-0.79

Ô

-0.78

ategory

-0.77

schild

-0.76

renheit

-0.76

urgy

-0.75

unta

-0.74

ourke

-0.73

lation

-0.73

POSITIVE LOGITS

 halves

1.51

 sides

1.40

 sexes

1.22

 thirds

1.14

 parties

1.08

fold

1.05

 Kore

1.00

 finalists

0.98

 extremes

0.98

 gentlemen

0.95

Activations Density 0.047%

the word "two" occurring in different contexts

instances of the word "two" in various contexts

No Comments

No Known Activations