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

alez

-0.75

SHIP

-0.73

laim

-0.72

aunders

-0.72

ategory

-0.69

ickr

-0.69

tsky

-0.67

anguage

-0.64

ocaust

-0.63

ismo

-0.63

POSITIVE LOGITS

 Andromeda

0.76

isSpecialOrderable

0.69

unic

0.66

pee

0.65

 Null

0.62

uffle

0.61

 biome

0.61

brace

0.61

dimension

0.60

Math

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.