INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Pg

-0.79

ÄŁ

-0.76

test

-0.70

status

-0.69

apple

-0.67

bre

-0.66

borough

-0.66

roxy

-0.66

 Yose

-0.66

Interstitial

-0.66

POSITIVE LOGITS

Cla

0.73

 where

0.72

 WHERE

0.64

 attracts

0.64

 collects

0.62

 sells

0.62

 Contracts

0.62

 Tasman

0.61

 Chim

0.61

 negoti

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.