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

plet

-0.66

CRA

-0.65

icester

-0.63

 conception

-0.60

ATIONAL

-0.59

 Zeit

-0.59

 recal

-0.59

 Rahul

-0.58

reg

-0.58

ris

-0.57

POSITIVE LOGITS

natureconservancy

0.89

sylv

0.80

 Cosponsors

0.78

 Hels

0.74

endum

0.73

inventory

0.72

ahime

0.70

agues

0.69

idding

0.68

knife

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.