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

 proport

-0.73

»Ĵ

-0.72

chwitz

-0.67

 classmates

-0.67

 reconc

-0.66

ptive

-0.63

ima

-0.62

 Intake

-0.62

olars

-0.61

 destro

-0.60

POSITIVE LOGITS

cover

0.70

 sleeper

0.69

ard

0.66

bidden

0.65

itary

0.63

gal

0.61

bull

0.61

ALE

0.59

 WARN

0.59

iesta

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.