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

lect

-0.81

isec

-0.69

Reviewer

-0.66

phabet

-0.65

wig

-0.64

olicy

-0.62

Vac

-0.61

ornia

-0.61

regation

-0.61

renheit

-0.61

POSITIVE LOGITS

atta

0.67

eri

0.66

 peanuts

0.65

ESH

0.64

ickers

0.62

 derby

0.62

daq

0.62

ICO

0.62

stri

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.