INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ãĥ³ãĤ¸

-0.70

 Gingrich

-0.66

 LIST

-0.64

)\

-0.63

 Treaty

-0.63

 Howard

-0.63

').

-0.62

ARCH

-0.62

GM

-0.62

 Racial

-0.61

POSITIVE LOGITS

rieve

0.76

finder

0.71

iard

0.67

aido

0.67

 coworkers

0.67

umat

0.66

amas

0.65

othal

0.63

olson

0.63

uyomi

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.