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

©¶æ

-0.76

rop

-0.67

apon

-0.63

lean

-0.62

intosh

-0.60

cium

-0.60

 energ

-0.59

 trad

-0.59

 vulner

-0.58

aud

-0.58

POSITIVE LOGITS

KEN

0.75

athom

0.69

\\\\\\\\

0.69

 Mubarak

0.66

Reviewer

0.63

Brow

0.61

 Anders

0.60

ocent

0.60

Thumbnail

0.59

HHHH

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.