INDEX

Explanations

words related to lenses and focusing

oai_token-act-pair · gpt-3.5-turbo

terms associated with camera lenses and optical properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TY

-0.78

BY

-0.75

lly

-0.72

onge

-0.69

alky

-0.66

DAY

-0.66

anqu

-0.66

avez

-0.64

 Chatt

-0.64

awar

-0.63

POSITIVE LOGITS

 lenses

1.10

 lens

1.08

 flares

1.02

 flare

0.95

linger

0.88

 aperture

0.83

Lens

0.82

 Lens

0.82

Cra

0.79

kies

0.78

Activations Density 0.018%

words related to lenses and focusing

terms associated with camera lenses and optical properties

No Comments

No Known Activations