INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

arthed

-0.79

endum

-0.71

*/

-0.70

Sleep

-0.69

 compuls

-0.68

-0.67

Ps

-0.66

successfully

-0.66

etus

-0.64

secution

-0.64

POSITIVE LOGITS

izon

0.73

 Haiti

0.72

 Ashe

0.71

 Router

0.67

 Rack

0.67

 landfill

0.67

 Fargo

0.66

 Nerd

0.66

 Nass

0.66

 Hudson

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.