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

opian

-0.83

ocado

-0.71

EMENT

-0.71

uten

-0.69

enance

-0.68

icial

-0.67

icians

-0.67

GMT

-0.66

atz

-0.66

forts

-0.65

POSITIVE LOGITS

sea

0.74

 scoop

0.64

SPA

0.63

 squat

0.63

 Hels

0.63

 bipolar

0.63

thy

0.61

cipline

0.60

thood

0.60

Single

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.