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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Pillar

-0.73

 bets

-0.71

reys

-0.71

ourney

-0.69

 Sins

-0.67

Seg

-0.66

azines

-0.65

heny

-0.62

nesday

-0.62

 graz

-0.61

POSITIVE LOGITS

requires

0.76

advertisement

0.73

aton

0.72

ARA

0.72

_.

0.71

PRESS

0.69

ATA

0.67

âĹ¼

0.67

âĺħâĺħ

0.66

employment

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.