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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 manif

-0.77

 intoxication

-0.68

Initialized

-0.67

 Wynne

-0.67

fell

-0.64

OPLE

-0.63

brow

-0.63

 retrie

-0.63

 youths

-0.62

 handling

-0.60

POSITIVE LOGITS

itionally

0.80

 Germ

0.77

hest

0.76

iliate

0.74

quished

0.74

èª

0.73

ibaba

0.72

 Siberian

0.70

acial

0.70

ãĥĳ

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.