INDEX

Explanations

references to camera lenses

oai_token-act-pair · gpt-3.5-turbo

terms related to optical lenses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

currency

-0.74

 Chatt

-0.65

lly

-0.65

uca

-0.65

ansom

-0.65

lishes

-0.64

 Carnegie

-0.61

alions

-0.60

encia

-0.60

 Sheet

-0.60

POSITIVE LOGITS

 lenses

1.20

 lens

1.19

 flares

1.17

 flare

1.06

 Lens

1.02

Cra

0.97

 glasses

0.93

 magnification

0.92

seeing

0.92

 optics

0.88

Activations Density 0.050%

references to camera lenses

terms related to optical lenses

No Comments

No Known Activations