INDEX

Explanations

references to locations or structures being inside of something

oai_token-act-pair · gpt-3.5-turbo

references to various locations

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

QL

-0.77

emale

-0.73

arcity

-0.73

folk

-0.73

eday

-0.71

wives

-0.71

ingle

-0.70

cific

-0.70

uten

-0.70

ocious

-0.69

POSITIVE LOGITS

 walls

1.09

 confines

1.08

 bubble

1.00

 doors

0.98

box

0.94

 cage

0.93

 envelope

0.91

 gates

0.91

 boxes

0.89

 mouths

0.86

Activations Density 0.122%

references to locations or structures being inside of something

references to various locations

No Comments

No Known Activations