INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

Psy

-0.74

older

-0.71

uxe

-0.69

-0.66

PET

-0.65

usters

-0.65

where

-0.64

 Dusk

-0.64

aution

-0.63

ãĥł

-0.63

POSITIVE LOGITS

lyn

0.75

pedia

0.69

RAFT

0.68

 Heisman

0.68

strap

0.68

quartered

0.66

aeper

0.65

isSpecialOrderable

0.64

FUL

0.64

 Klux

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.