INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ilda

-0.83

yen

-0.79

 tremend

-0.79

osuke

-0.77

 insepar

-0.76

elin

-0.75

arius

-0.75

adia

-0.74

ouk

-0.72

 neighbour

-0.72

POSITIVE LOGITS

\":

0.73

 Codec

0.69

Generic

0.67

 contraceptives

0.66

 Celeb

0.66

 contraception

0.65

OTOS

0.65

 PubMed

0.65

 Verify

0.64

GOP

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.