INDEX

Explanations

specific structural elements or programming syntax in a document

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<eos>

-0.60

 JADX

-0.56

-0.51

 […]

-0.47

 acontecer

-0.45

 möjligt

-0.42

 gezin

-0.42

 senare

-0.41

impin

-0.40

larak

-0.40

POSITIVE LOGITS

 Normdatei

0.77

createCanvas

0.75

 AssemblyCulture

0.74

Искәрмәләр

0.74

aarrggbb

0.74

Lähteet

0.73

DockStyle

0.70

Personendaten

0.70

Rüyada

0.69

 iſt

0.69

Activations Density 0.044%

specific structural elements or programming syntax in a document

No Comments

No Known Activations