INDEX

Explanations

terms and structures related to function arguments in programming

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 houſe

-0.64

withIdentifier

-0.62

Portail

-0.61

 Houſe

-0.59

 مرئيه

-0.58

 myſelf

-0.58

 كومونز

-0.55

IBOutlet

-0.55

 itſelf

-0.55

 pleaſure

-0.55

POSITIVE LOGITS

 nargin

0.74

arguments

0.65

stdarg

0.60

argout

0.53

 arguments

0.52

varargin

0.50

 argumentos

0.47

AppMethodBeat

0.47

 voces

0.42

 PyTuple

0.41

Activations Density 0.002%

terms and structures related to function arguments in programming

No Comments

No Known Activations