INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

oho

-0.76

inks

-0.71

ourt

-0.71

asa

-0.71

Ã¯

-0.71

isphere

-0.71

quet

-0.70

aday

-0.69

 mathemat

-0.69

ashtra

-0.69

POSITIVE LOGITS

iate

0.70

iP

0.69

charg

0.66

 Intake

0.62

rock

0.62

addons

0.61

warm

0.61

 Variant

0.61

 Volunteers

0.61

 fentanyl

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.