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

 Cath

-0.71

eon

-0.68

rador

-0.67

Xan

-0.66

ourt

-0.64

 quer

-0.63

rag

-0.62

ante

-0.60

 thrill

-0.59

ocr

-0.58

POSITIVE LOGITS

vernment

0.84

fox

0.75

Alert

0.71

ibr

0.70

eworks

0.69

icism

0.68

ideshow

0.67

sonian

0.66

oice

0.66

facts

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.