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

panel

-0.78

CHO

-0.74

 advis

-0.68

EM

-0.66

ibly

-0.65

worthiness

-0.64

HA

-0.63

ibles

-0.62

ABLE

-0.62

POSITIVE LOGITS

©¶æ

0.83

ĸļ

0.75

rea

0.71

 Peaks

0.68

 Rats

0.66

quartered

0.65

alg

0.64

\">

0.63

escent

0.63

":["

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.