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

 Seym

-0.85

swick

-0.80

ilib

-0.79

 Volunte

-0.77

cair

-0.75

KER

-0.70

mercial

-0.69

pron

-0.68

Correct

-0.67

DOC

-0.64

POSITIVE LOGITS

thora

0.74

 harass

0.73

 frank

0.71

 grav

0.69

riz

0.69

 masturb

0.67

 rampage

0.67

 morale

0.65

 inciner

0.65

 wrath

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.