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

gins

-0.71

é¾įåĸļå£«

-0.71

 resil

-0.71

orem

-0.71

amer

-0.70

eatures

-0.70

 antioxid

-0.69

INS

-0.68

 ACTIONS

-0.66

 seiz

-0.66

POSITIVE LOGITS

 Shank

0.64

Cru

0.64

Kub

0.61

Å

0.61

quart

0.60

Aux

0.60

 pursuant

0.58

Nug

0.56

 seldom

0.56

Sk

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.