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

adic

-0.70

TPPStreamerBot

-0.70

apolis

-0.70

iquid

-0.68

abies

-0.64

ificant

-0.64

 favour

-0.63

 contra

-0.63

Steel

-0.62

vidia

-0.62

POSITIVE LOGITS

 Journals

0.77

 Authorization

0.74

 MacArthur

0.71

 DRAG

0.68

 Melody

0.65

 Editing

0.65

âĪ

0.63

 Rout

0.63

 Codex

0.63

 Locations

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.