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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

relation

-0.80

qqa

-0.80

 tremend

-0.76

otype

-0.72

fields

-0.71

atto

-0.70

ching

-0.68

ngth

-0.66

Í

-0.66

bi

-0.66

POSITIVE LOGITS

utherford

0.81

utory

0.70

 Admir

0.65

RSS

0.65

uyomi

0.65

 Vapor

0.64

imov

0.62

verning

0.62

flation

0.62

duino

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.