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

HCR

-0.76

 repr

-0.70

bestos

-0.65

cott

-0.65

 constitu

-0.65

 destination

-0.63

 Pipeline

-0.63

 resignation

-0.61

«ĺ

-0.61

 Lafayette

-0.61

POSITIVE LOGITS

iths

0.76

Dat

0.69

ply

0.66

ins

0.65

Äĵ

0.65

 Milky

0.64

 Yamato

0.64

inis

0.64

hews

0.64

wax

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.