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

erest

-0.73

rave

-0.69

 Hitch

-0.69

NetMessage

-0.69

 Roads

-0.66

roth

-0.66

Ń·

-0.64

 Thing

-0.62

 Southwest

-0.61

OOK

-0.61

POSITIVE LOGITS

iod

0.86

availability

0.80

etics

0.70

 endors

0.70

izes

0.66

Ak

0.65

 constitutes

0.64

ciplinary

0.63

 execut

0.63

iar

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.