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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

itiveness

-0.75

hesis

-0.70

ths

-0.69

itution

-0.68

uation

-0.67

amped

-0.64

ugg

-0.64

isons

-0.64

aud

-0.63

iannopoulos

-0.63

POSITIVE LOGITS

fol

0.70

tale

0.63

cules

0.62

 Blooming

0.61

edia

0.60

 Vanilla

0.58

 Released

0.58

 pregn

0.58

 endors

0.57

odor

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.