INDEX

Explanations

the word "lump."

oai_token-act-pair · gpt-3.5-turbo

references to the word "lump" 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 @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

Cu

-0.73

ires

-0.71

ande

-0.67

Domin

-0.64

 Schmidt

-0.63

OPE

-0.63

 Bravo

-0.62

oute

-0.61

âĢ¢âĢ¢âĢ¢âĢ¢

-0.61

Press

-0.61

POSITIVE LOGITS

 lump

3.82

 Lump

1.87

alog

1.13

 grouped

0.96

 misrepresent

0.95

 stereotyp

0.86

 pigeon

0.85

 bump

0.84

 opportun

0.82

 blob

0.81

Activations Density 0.021%

the word "lump."

references to the word "lump" in various contexts

No Comments

No Known Activations