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

throp

-0.72

Closure

-0.69

versive

-0.68

ruction

-0.67

Statement

-0.66

angered

-0.66

RET

-0.66

Scotland

-0.66

INAL

-0.65

phia

-0.65

POSITIVE LOGITS

elson

0.77

 prest

0.66

 religiously

0.63

anwhile

0.61

tta

0.60

 ditch

0.60

 capacitor

0.59

nexus

0.58

onga

0.58

 spons

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.