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

ricks

-0.92

stones

-0.76

ework

-0.66

stone

-0.66

anch

-0.65

elines

-0.64

onna

-0.64

nar

-0.64

kun

-0.64

stals

-0.64

POSITIVE LOGITS

 territ

0.75

Raz

0.67

UNCH

0.66

 skelet

0.63

 Atom

0.59

 Judah

0.59

jee

0.59

 avocado

0.59

 irrig

0.58

 convol

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.