INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ould

-0.75

 neighb

-0.68

 behavi

-0.68

 advisory

-0.67

jri

-0.67

 warr

-0.67

 marqu

-0.67

 Academy

-0.65

vironment

-0.64

ogle

-0.63

POSITIVE LOGITS

asts

0.77

Bra

0.72

ources

0.71

asting

0.70

ãĥı

0.69

orically

0.67

States

0.67

Autom

0.66

iles

0.65

andra

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.