INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Ô

-1.00

quished

-0.91

CTV

-0.70

Winner

-0.69

edIn

-0.68

CNN

-0.66

 contestant

-0.64

edin

-0.64

ophon

-0.63

 atheist

-0.63

POSITIVE LOGITS

orage

0.72

 Yard

0.65

office

0.61

 Tail

0.61

 lodge

0.60

 cannabin

0.59

 Hatch

0.58

olitan

0.57

poke

0.57

yard

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.