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

unctions

-0.73

 Pupp

-0.72

 Survivors

-0.69

 Judd

-0.68

ulas

-0.68

 Boat

-0.66

iors

-0.65

irs

-0.65

ebus

-0.65

qa

-0.65

POSITIVE LOGITS

 allocated

0.74

 allocation

0.72

MET

0.71

 GOODMAN

0.68

 realise

0.67

\">

0.65

"]=>

0.65

 positively

0.64

haven

0.64

 muster

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.