INDEX

Explanations

references to specific coding variables and structured data formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 ProtoMessage

-0.70

)$}

-0.67

complexContent

-0.65

PONENTS

-0.64

tzmann

-0.62

شون

-0.62

 Schell

-0.61

JUDGE

-0.59

donate

-0.59

bekistan

-0.59

POSITIVE LOGITS

rungsseite

0.66

 alrededores

0.60

 ejus

0.59

 Lijst

0.58

 nicio

0.58

 figliu

0.58

agisse

0.58

 neceſſ

0.57

LEncoder

0.56

 ISNI

0.55

Activations Density 0.106%

references to specific coding variables and structured data formats

No Comments

No Known Activations