INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Guid

-0.70

 carbohyd

-0.68

gur

-0.67

VERTISEMENT

-0.63

 scaven

-0.58

 mobilization

-0.58

DonaldTrump

-0.58

 Clouds

-0.58

 totaled

-0.57

 SOFTWARE

-0.57

POSITIVE LOGITS

ovember

0.82

love

0.81

razil

0.77

stead

0.77

ethical

0.75

yre

0.73

ishi

0.72

itta

0.71

uesday

0.70

amina

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.