INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

cest

-0.66

 neighbors

-0.66

 comprom

-0.66

 precursor

-0.66

 Dynam

-0.64

 inability

-0.61

 asshole

-0.60

 habitual

-0.60

 Ratt

-0.60

 unden

-0.60

POSITIVE LOGITS

sbm

0.80

ozy

0.77

amera

0.77

]);

0.75

ffe

0.74

displayText

0.72

_-_

0.71

"]=>

0.70

fman

0.70

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.