INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

tera

-0.71

osit

-0.69

dust

-0.67

soDeliveryDate

-0.64

phot

-0.64

vern

-0.63

Override

-0.63

itect

-0.60

OPA

-0.59

ISTORY

-0.59

POSITIVE LOGITS

 gobl

0.73

Lis

0.70

 Bros

0.69

 comprom

0.67

 trave

0.66

åĭ

0.65

jri

0.64

 sovere

0.64

 destro

0.64

 regress

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.