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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 toler

-0.76

nel

-0.74

cair

-0.74

anooga

-0.73

 Leban

-0.71

 guerrilla

-0.70

omore

-0.69

vou

-0.64

nels

-0.64

BEL

-0.64

POSITIVE LOGITS

veyard

0.75

oster

0.71

asons

0.71

requency

0.68

dfx

0.66

atern

0.65

uably

0.65

genre

0.64

ocyte

0.63

esan

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.