INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

rika

-0.71

cair

-0.69

dit

-0.66

}"

-0.65

alogue

-0.64

cape

-0.64

dating

-0.63

swer

-0.63

ranean

-0.63

pse

-0.62

POSITIVE LOGITS

ãĤ¨ãĥ«

0.73

oit

0.67

 spoilers

0.67

 heel

0.62

 LAPD

0.59

 exploits

0.59

Import

0.59

'[

0.58

 deform

0.58

Chicago

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.