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

ãĤ¡

-0.90

ãĥĺ

-0.90

ç«

-0.80

æ©

-0.77

 Pengu

-0.74

ð

-0.74

ãĥ¬

-0.72

ãĤ§

-0.71

 juven

-0.71

ãĥı

-0.70

POSITIVE LOGITS

allah

0.71

isson

0.70

omy

0.66

 guiActiveUnfocused

0.65

orm

0.65

oping

0.61

ovan

0.61

ily

0.61

deal

0.60

verend

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.