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

OND

-0.78

IST

-0.68

 Jord

-0.64

UES

-0.62

laun

-0.61

IPP

-0.61

Cmd

-0.61

roots

-0.60

 Airl

-0.60

 Cherokee

-0.59

POSITIVE LOGITS

ername

0.71

 teasp

0.69

ventus

0.69

ellectual

0.67

ptin

0.65

cliffe

0.65

ibling

0.64

mitter

0.64

ividual

0.64

rotein

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.