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

Alert

-0.71

 srfAttach

-0.69

edom

-0.68

 catalog

-0.67

 mathemat

-0.65

ophon

-0.63

SOURCE

-0.60

Haj

-0.60

ollen

-0.60

MAT

-0.59

POSITIVE LOGITS

NZ

0.70

pai

0.64

wil

0.62

ski

0.60

 wast

0.58

rarily

0.58

ah

0.58

EStreamFrame

0.58

NZ

0.58

 McGr

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.