INDEX

Explanations

elements related to linguistic structures and classifications

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

Linguistics and grammar

np_acts-logits-general · gemini-2.0-flash

language grammar and syntax

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

 DBNull

-0.51

 Fotografie

-0.48

 raccont

-0.47

TargetException

-0.45

ApiModelProperty

-0.45

getCmp

-0.44

 calculées

-0.44

 scouting

-0.44

iddhartha

-0.44

 photographie

-0.43

POSITIVE LOGITS

 gramm

1.00

 linguistic

1.00

 lingu

0.94

 grammar

0.89

 grammatical

0.89

 linguistics

0.86

 Linguistics

0.84

 phonetic

0.84

 Grammar

0.83

 Sprach

0.82

Activations Density 0.342%

elements related to linguistic structures and classifications

Linguistics and grammar

language grammar and syntax

No Comments

No Known Activations