INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ATCH

-0.67

 monitors

-0.67

âĸ¬âĸ¬

-0.67

Reloaded

-0.66

Scroll

-0.66

Particip

-0.66

 Bulldogs

-0.65

-+-+

-0.64

eer

-0.63

 Western

-0.60

POSITIVE LOGITS

solid

0.72

ibo

0.71

forms

0.71

hematic

0.67

agher

0.64

emb

0.64

acters

0.64

gorith

0.64

hran

0.63

rait

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.