INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

},{"

-0.74

hare

-0.67

hawk

-0.66

 tallest

-0.65

tis

-0.61

allery

-0.60

otics

-0.59

plex

-0.59

iatrics

-0.58

bush

-0.58

POSITIVE LOGITS

 Reload

0.79

Lod

0.70

vern

0.69

culus

0.68

ppo

0.67

ÄŁ

0.65

 Papa

0.64

 Kens

0.63

 Provision

0.62

Cue

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.