INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Siem

-0.65

olicy

-0.64

igible

-0.62

 Memor

-0.62

 Prompt

-0.62

Neg

-0.60

Sie

-0.59

Leh

-0.59

 Stead

-0.59

Nil

-0.59

POSITIVE LOGITS

ATED

0.71

OPLE

0.70

UFF

0.70

PDATED

0.69

izer

0.69

IENCE

0.68

llah

0.68

 ILCS

0.68

iago

0.68

APTER

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.