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

ciation

-0.71

 Cosponsors

-0.69

 Agric

-0.66

TIT

-0.65

ANT

-0.65

 POLITICO

-0.65

journal

-0.64

olicy

-0.63

events

-0.62

tical

-0.62

POSITIVE LOGITS

 fascination

0.77

anu

0.75

ril

0.75

 throb

0.74

 hump

0.74

 envy

0.70

 womb

0.68

 blurred

0.68

 blurry

0.68

lasses

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.