INDEX

Explanations

coding-related terms and components related to API functions in a programming context

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

<start_of_turn>user

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

TestingModule

-0.37

jer

-0.33

ger

-0.32

id

-0.32

 tide

-0.32

id

-0.31

 jala

-0.31

pad

-0.30

 tere

-0.30

 extension

-0.30

POSITIVE LOGITS

 kasarigan

0.82

smithy

0.75

NameInMap

0.63

StructEnd

0.60



0.56

httphttps

0.56

 informée

0.54



0.54

scriptcase

0.54

 Италијани

0.53

Activations Density 0.063%

coding-related terms and components related to API functions in a programming context

<start_of_turn>user

No Comments

No Known Activations