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

ÃŃs

-0.70

 Inquis

-0.68

Rey

-0.66

idi

-0.59

 Bris

-0.58

 Ingram

-0.58

SB

-0.57

Hun

-0.56

phas

-0.56

moderate

-0.56

POSITIVE LOGITS

entimes

0.86

VERTISEMENT

0.70

anol

0.68

illon

0.65

Laughs

0.64

 gearing

0.62

inel

0.61

ppelin

0.61

idents

0.61

anu

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.