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

RY

-0.79

ACTED

-0.78

TEXT

-0.78

FN

-0.78

externalActionCode

-0.77

WM

-0.76

CLAIM

-0.75

fn

-0.74

NRS

-0.73

âĢ¢âĢ¢

-0.73

POSITIVE LOGITS

 deserts

0.74

ahime

0.74

adesh

0.72

 unused

0.68

 climates

0.67

 seam

0.66

 theat

0.65

unia

0.65

imore

0.63

 curves

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.