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

pmwiki

-1.01

accompan

-0.79

votes

-0.76

å¥³

-0.75

ESA

-0.73

ifix

-0.71

lihood

-0.71

cone

-0.70

swing

-0.70

hovah

-0.69

POSITIVE LOGITS

Rao

0.73

 Sham

0.71

 Prin

0.69

 Amir

0.67

 Spice

0.65

selves

0.64

arov

0.63

neum

0.63

Gy

0.63

Pri

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.