INDEX

Explanations

terms related to the integration and significance of parts or components in various contexts

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

Possessive pronouns followed by nouns

np_acts-logits-general · gemini-2.0-flash

part of

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 helyez

-0.57

AddHtmlAttribute

-0.55

RetentionPolicy

-0.55

awaiter

-0.54

Pautan

-0.49

Varint

-0.49

 ligiloj

-0.49

OGND

-0.49

jsonwebtoken

-0.48

AndroidJUnit

-0.47

POSITIVE LOGITS

 equation

1.00

 repertoire

0.95

 arsenal

0.91

mix

0.73

 lexicon

0.67

équation

0.66

equation

0.65

 proceedings

0.65

 purview

0.65

 repertorio

0.65

Activations Density 0.391%

terms related to the integration and significance of parts or components in various contexts

Possessive pronouns followed by nouns

part of

No Comments

No Known Activations