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

arthed

-0.79

£ı

-0.75

oa

-0.75

KO

-0.69

Mol

-0.67

Klu

-0.65

ĸļ

-0.65

rower

-0.65

 Stam

-0.64

UL

-0.64

POSITIVE LOGITS

 accommod

0.65

 Scrolls

0.62

 responsiveness

0.61

Closure

0.59

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

0.59

 mantle

0.59

 undo

0.59

agos

0.58

ENCY

0.58

 func

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.