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

achu

-0.82

icz

-0.74

ocol

-0.73

imum

-0.71

allo

-0.71

swers

-0.71

 Samoa

-0.69

oho

-0.69

ricanes

-0.68

osed

-0.68

POSITIVE LOGITS

 perk

0.67

 wonders

0.66

 whim

0.66

TextColor

0.64

 heartbeat

0.63

bleacher

0.63

 whisper

0.62

 deduction

0.61

 spotting

0.59

 watch

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.