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

 Extend

-0.66

 Opportun

-0.61

 Moroc

-0.61

allows

-0.61

letes

-0.59

 Jets

-0.59

WAYS

-0.58

 Fant

-0.58

 DRAG

-0.58

 Expand

-0.58

POSITIVE LOGITS

istry

0.82

agall

0.73

omet

0.71

aban

0.71

LEY

0.70

icum

0.69

anus

0.67

icle

0.67

added

0.66

clave

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.