INDEX

Explanations

technical terms and identifiers related to data structures and programming concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sprend

-0.42

PMailer

-0.41

 ondas

-0.40

 disant

-0.39

 isKindOfClass

-0.38

gé

-0.38

(&

-0.38

 hvilken

-0.37

nloa

-0.37

 avesse

-0.36

POSITIVE LOGITS

SharedCtor

0.97

featureID

0.85

хьтан

0.84

contentLoaded

0.80

 للاسماء

0.79

adpleegd

0.77

GEBURTSDATUM

0.77

parsedMessage

0.76

transQ

0.76

raszamy

0.71

Activations Density 1.007%

technical terms and identifiers related to data structures and programming concepts

No Comments

No Known Activations