INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

earch

-0.82

ishers

-0.75

cients

-0.74

ordes

-0.70

apon

-0.66

ARS

-0.66

 explorers

-0.66

Ort

-0.66

ians

-0.65

aiman

-0.64

POSITIVE LOGITS

 whiff

0.72

dylib

0.67

../

0.66

 Codec

0.66

tle

0.62

tta

0.62

tiny

0.62

TextColor

0.61

 riding

0.61

sample

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.