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

ouf

-0.83

fen

-0.83

atsuki

-0.77

obile

-0.76

emis

-0.75

ussen

-0.72

obar

-0.71

theless

-0.71

ocl

-0.70

ettel

-0.69

POSITIVE LOGITS

 Chocobo

0.69

 Doodle

0.63

 Piet

0.63

benefit

0.63

Boo

0.61

 Chaff

0.61

 Proposition

0.61

 Angelo

0.60

 Maze

0.60

verse

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.