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

srf

-0.72

bett

-0.71

terday

-0.69

bledon

-0.67

areth

-0.67

 carbohyd

-0.67

onge

-0.67

byn

-0.65

allowed

-0.65

ippi

-0.65

POSITIVE LOGITS

Ã±a

0.77

 sentimental

0.71

 shepherd

0.70

Footnote

0.68

 farewell

0.68

encia

0.68

taboola

0.67

 pity

0.65

à©

0.64

orian

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.