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

 Revis

-0.77

acon

-0.73

athing

-0.73

foundation

-0.73

 repealing

-0.68

idas

-0.68

jab

-0.67

antz

-0.67

guard

-0.67

jad

-0.65

POSITIVE LOGITS

YY

0.74

etheless

0.72

OUN

0.71

opian

0.69

DEM

0.68

 DRAG

0.65

ounded

0.64

 Plat

0.64

²¾

0.63

PLAY

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.