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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ABE

-0.66

ELF

-0.64

glers

-0.63

dn

-0.63

nesia

-0.62

hammad

-0.60

mum

-0.60

 decad

-0.59

çĶ°

-0.59

Jose

-0.57

POSITIVE LOGITS

geist

0.69

ollar

0.69

0.68

0.67

[*]

0.65

 Gener

0.65

 Miko

0.64

 Rarity

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.