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

 Jagu

-0.75

tnc

-0.74

 corrid

-0.72

 reconnaissance

-0.71

aida

-0.68

alus

-0.68

 unaccompanied

-0.67

 Airways

-0.67

ijn

-0.66

 Americ

-0.64

POSITIVE LOGITS

mg

0.78

emies

0.75

<<

0.75

pg

0.72

âĨ

0.72

{}

0.70

oppable

0.65

<<

0.65

âĨĳ

0.65

âĸł

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.