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

ÃĥÃĤ

-0.71

 sleeper

-0.70

agascar

-0.69

VL

-0.67

ctic

-0.66

PLAY

-0.64

DW

-0.61

riors

-0.59

 toughest

-0.58

#$

-0.57

POSITIVE LOGITS

ku

0.69

 Portug

0.69

ento

0.68

oving

0.68

tel

0.67

stones

0.66

arten

0.66

frey

0.66

antes

0.66

ĪĴ

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.