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

ector

-0.74

IOR

-0.69

ior

-0.68

aan

-0.68

fa

-0.68

acker

-0.68

lass

-0.67

hov

-0.67

oyal

-0.66

é¾

-0.66

POSITIVE LOGITS

 ages

0.87

ciating

0.86

 Moonlight

0.74

 Inquisition

0.71

 Eclipse

0.70

icans

0.67

Yang

0.66

etimes

0.65

 Clockwork

0.64

geries

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.