INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Viol

-0.75

Plot

-0.74

Broad

-0.74

 unfocusedRange

-0.66

Operation

-0.63

Counter

-0.62

ilts

-0.62

 Queens

-0.62

 violation

-0.61

 è£ıè¦ļéĨĴ

-0.60

POSITIVE LOGITS

obyl

0.80

kefeller

0.76

elong

0.75

ipeg

0.73

amara

0.73

wcs

0.72

berus

0.72

alore

0.71

escription

0.70

arily

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.