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

avia

-0.73

-0.69

 Sierra

-0.63

oscope

-0.62

 Clara

-0.60

ania

-0.60

mp

-0.59

oops

-0.59

opter

-0.59

POSITIVE LOGITS

PsyNetMessage

0.74

 DARK

0.68

STRUCT

0.67

ãĤ©

0.67

actionDate

0.66

SpaceEngineers

0.66

Pie

0.66

dinand

0.64

erg

0.63

 Ging

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.