INDEX

Explanations

references to physical ropes, wires, or similar objects

oai_token-act-pair · gpt-3.5-turbo

references to ropes and related equipment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ropolitan

-0.91

ctuary

-0.88

ãĥ´

-0.81

apolis

-0.78

esson

-0.76

hem

-0.75

ãĥĨãĤ£

-0.74

ansion

-0.73

insula

-0.72

itia

-0.71

POSITIVE LOGITS

 rope

1.00

 bondage

0.97

 strap

0.89

 ropes

0.83

 Grip

0.82

asso

0.81

 climbs

0.80

 ladder

0.79

 climbing

0.78

 snakes

0.76

Activations Density 0.029%

references to physical ropes, wires, or similar objects

references to ropes and related equipment

No Comments

No Known Activations