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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

onomy

-0.79

á

-0.69

wolf

-0.65

onomic

-0.64

ESV

-0.64

aintain

-0.64

anus

-0.63

NK

-0.62

icum

-0.62

Obj

-0.61

POSITIVE LOGITS

 Doll

0.73

artifacts

0.68

igg

0.66

 Yesterday

0.66

 Sands

0.64

inces

0.63

 dolls

0.62

mast

0.60

 Lizard

0.60

 Labyrinth

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.