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

ties

-0.82

 Coffin

-0.73

bil

-0.67

ynski

-0.64

istries

-0.63

 fatig

-0.62

ence

-0.60

 ceilings

-0.60

forming

-0.60

batch

-0.58

POSITIVE LOGITS

eworks

0.83

ickr

0.79

isSpecialOrderable

0.76

PDATE

0.75

ERT

0.70

reci

0.70

tnc

0.69

udeb

0.69

å£

0.68

Ni

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.