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

illac

-0.82

ebted

-0.80

oton

-0.79

regor

-0.78

 Tanz

-0.76

istors

-0.71

iership

-0.70

phies

-0.69

amiya

-0.69

erella

-0.69

POSITIVE LOGITS

educ

0.82

II

0.77

SD

0.74

intend

0.68

sic

0.64

intendent

0.64

Eng

0.64

Te

0.63

ificantly

0.62

TE

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.