INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Neal

-0.82

scientific

-0.79

æ©Ł

-0.74

 Rapp

-0.74

advertising

-0.71

ĨĴ

-0.69

humans

-0.69

Else

-0.68

osate

-0.68

hyde

-0.67

POSITIVE LOGITS

 unfold

0.75

Tokens

0.71

 badges

0.68

 tabs

0.67

 fray

0.63

 stickers

0.62

 realised

0.62

 troop

0.62

 vacc

0.61

 greets

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.