INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Sovere

-0.78

orp

-0.74

pos

-0.69

plex

-0.68

zzle

-0.66

 Reprodu

-0.64

IPM

-0.64

PAR

-0.63

itars

-0.63

xon

-0.62

POSITIVE LOGITS

rained

0.71

ets

0.70

onen

0.69

 planner

0.67

 worn

0.66

eting

0.66

owed

0.65

ynski

0.65

sic

0.64

 foot

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.