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

eto

-0.68

 Cart

-0.68

scope

-0.68

SEN

-0.63

iframe

-0.62

 guiActiveUnfocused

-0.61

irlf

-0.61

 competent

-0.60

 Compass

-0.60

ESC

-0.60

POSITIVE LOGITS

ibaba

0.89

tymology

0.89

yss

0.74

 suprem

0.71

raviolet

0.71

 rall

0.70

aturdays

0.70

rb

0.69

CVE

0.69

alach

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.