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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

terday

-0.76

 independ

-0.68

 accur

-0.68

ombat

-0.68

oit

-0.67

cham

-0.67

hesda

-0.67

 preval

-0.66

Dak

-0.65

 liberated

-0.65

POSITIVE LOGITS

geist

0.81

home

0.75

Neal

0.70

ãĥį

0.67

 Webs

0.66

Sil

0.64

glass

0.64

ious

0.63

igans

0.63

block

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.