INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

Rated

-0.76

aver

-0.70

onson

-0.69

ICH

-0.69

lie

-0.68

erve

-0.68

Interstitial

-0.67

IDER

-0.66

oons

-0.65

ammy

-0.64

POSITIVE LOGITS

EStreamFrame

0.77

 Cabrera

0.74

 Parties

0.62

arthed

0.60

 arbitration

0.59

 Celebrity

0.59

ukong

0.58

rament

0.58

aters

0.58

glers

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.