INDEX

Explanations

function calls related to resetting and clearing settings or data in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 FileInputStream

-0.74

 engraçadas

-0.72

 piaggio

-0.69

లాలు

-0.69

 GetEnumerator

-0.69

 âgées

-0.67

 ddelweddau

-0.66

 Interpolation

-0.66

nourriture

-0.65

Życiorys

-0.64

POSITIVE LOGITS

 reset

0.91

 Reset

0.85

 Clear

0.82

 clear

0.80

Reset

0.79

reset

0.77

Clear

0.76

 resets

0.73

RESET

0.69

 clears

0.68

Activations Density 0.092%

function calls related to resetting and clearing settings or data in a programming context

No Comments

No Known Activations