INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Lonely

-0.69

bestos

-0.68

oline

-0.66

¿½

-0.66

onica

-0.64

ãĤ¡

-0.64

lin

-0.63

 Flame

-0.62

ometry

-0.61

onding

-0.60

POSITIVE LOGITS

peg

0.80

çīĪ

0.73

natureconservancy

0.67

 fixme

0.62

ourke

0.60

ithing

0.60

 perk

0.60

sha

0.60

 snap

0.59

å§«

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.