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

iven

-0.79

 Unified

-0.75

ãĤ¡

-0.73

å¥³

-0.71

rica

-0.71

advertisement

-0.69

maps

-0.67

MH

-0.67

rika

-0.67

MQ

-0.67

POSITIVE LOGITS

TTL

0.74

pmwiki

0.70

ovember

0.68

Äį

0.66

 ceilings

0.66

 concess

0.66

 contem

0.65

zek

0.64

zech

0.64

 exha

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.