INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ÙĴ

-0.77

Tile

-0.74

Laughs

-0.69

sworth

-0.68

Cur

-0.65

ļé

-0.62

-0.59

Deal

-0.59

 Verse

-0.59

ens

-0.59

POSITIVE LOGITS

obyl

0.76

agna

0.74

reporting

0.71

ouls

0.69

nai

0.66

ndra

0.65

unks

0.65

RNA

0.65

analysis

0.65

berman

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.