INDEX

Explanations

function calls and object methods related to image processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

verwijspagina

-1.01

oredCriteria

-0.90

Efq

-0.84

hoeddwyd

-0.78

 Paglinawan

-0.76

 becauſe

-0.75

Personensuche

-0.73

 itſelf

-0.73

danno

-0.72

 myſelf

-0.71

POSITIVE LOGITS

cv

0.98

cv

0.96

opencv

0.92

plt

0.92

plt

0.78

CV

0.75

CV

0.65

Cv

0.61

pageId

0.59

balloon

0.58

Activations Density 0.051%

function calls and object methods related to image processing

No Comments

No Known Activations