INDEX

Explanations

identifiers related to programming elements or objects

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

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

1,048,576

Data Type

float32

Hook Name

blocks.12.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

textTheme

-0.58

ulisan

-0.52

RetentionPolicy

-0.49

XtraReports

-0.47

avadoc

-0.47

XtraEditors

-0.47

Dış

-0.46

ỡng

-0.46

umnos

-0.46

gouv

-0.45

POSITIVE LOGITS

0.68

AddTagHelper

0.65

 समीक्षक

0.59

 bezeichneter

0.58

 <<<<<<<<<<<<<<

0.58

Последние

0.57

 transfieras

0.56

Efq

0.56

 disambiguazione

0.54

 mxArray

0.54

Activations Density 0.007%

identifiers related to programming elements or objects

No Comments

No Known Activations