INDEX

Explanations

compound words related to traps

oai_token-act-pair · gpt-3.5-turbo

references to traps or trapdoors

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

issance

-0.91

edly

-0.89

sis

-0.85

verty

-0.70

kees

-0.70

ositories

-0.68

hip

-0.65

played

-0.64

league

-0.63

sports

-0.63

POSITIVE LOGITS

door

1.42

doors

1.31

idon

0.87

finding

0.86

 Hole

0.76

 traps

0.76

resses

0.70

 trap

0.70

 trapping

0.69

izons

0.67

Activations Density 0.055%

compound words related to traps

references to traps or trapdoors

No Comments

No Known Activations