INDEX

Explanations

objects or tools related to visual perception, such as lenses and cameras

oai_token-act-pair · gpt-3.5-turbo

references to lenses 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

BY

-0.76

TY

-0.73

lly

-0.70

 Chatt

-0.68

avez

-0.68

anqu

-0.64

quo

-0.63

onge

-0.63

awar

-0.62

Tenn

-0.62

POSITIVE LOGITS

 flares

1.12

 lens

1.08

 lenses

1.05

 flare

0.98

linger

0.85

horn

0.85

Lens

0.85

 Mechdragon

0.84

 Lens

0.83

 aperture

0.82

Activations Density 0.011%

objects or tools related to visual perception, such as lenses and cameras

references to lenses in various contexts

No Comments

No Known Activations