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

 Represent

-0.76

 ................

-0.69

 Bunker

-0.66

\-

-0.66

suff

-0.63

 Languages

-0.62

 Rehab

-0.61

statement

-0.59

uilding

-0.59

 unemploy

-0.58

POSITIVE LOGITS

ihar

0.82

 Dragonbound

0.74

pai

0.73

soDeliveryDate

0.73

enum

0.69

arily

0.69

stice

0.67

 awoken

0.66

yx

0.65

acho

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.