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

ugu

-0.85

Ð´

-0.75

odor

-0.73

bitcoin

-0.70

inct

-0.69

pload

-0.68

gang

-0.67

ickey

-0.67

claw

-0.66

ienne

-0.66

POSITIVE LOGITS

 Advocate

0.68

Untitled

0.67

 Builder

0.67

 Allows

0.67

 sidx

0.66

ļéĨĴ

0.66

HER

0.66

dies

0.65

ishable

0.64

Ĥİ

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.