INDEX

Explanations

terms related to functions and functional forms in various contexts

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

mathematical or computational "functions"

np_acts-logits-general · gemini-2.0-flash

function and its derivations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

$_['

-0.76

 Disagree

-0.69

InputBorder

-0.65

 unknownFields

-0.60

idopsis

-0.58

twimg

-0.56

INCREF

-0.56

 Marat

-0.55

jsonwebtoken

-0.55

 onSave

-0.55

POSITIVE LOGITS

ality

0.79

 functions

0.76

ally

0.68

functions

0.66

erals

0.65

alities

0.65

nelle

0.64

tional

0.62

 Functions

0.61

jonal

0.59

Activations Density 0.129%

terms related to functions and functional forms in various contexts

mathematical or computational "functions"

function and its derivations

No Comments

No Known Activations