INDEX

Explanations

terms related to memory storage and cognitive processes

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

Linguistics, language, and grammar

np_acts-logits-general · gemini-2.0-flash

language and linguistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.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

OGND

-0.61

CloseOperation

-0.58

 للاسماء

-0.57

BufferException

-0.57

SaveVideo

-0.56

DoubleQuotes

-0.56

 ContentValues

-0.56

 BoxDecoration

-0.54

 surla

-0.53

POSITIVE LOGITS

 linguistics

0.77

 linguistic

0.76

 Linguistics

0.69

 language

0.67

 linguistique

0.65

 lingü

0.65

 lingu

0.64

 Language

0.62

 speech

0.61

 grammar

0.61

Activations Density 1.036%

terms related to memory storage and cognitive processes

Linguistics, language, and grammar

language and linguistics

No Comments

No Known Activations