INDEX

Explanations

references to programming functions and methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 Roskov

-0.99

EndGlobalSection

-0.82



-0.74

 intptr

-0.70

ibol

-0.69

PyExc

-0.69

 للمعارف

-0.69

findpost

-0.66

RTGC

-0.65



-0.65

POSITIVE LOGITS

 initWithFrame

0.45

 كومونز

0.44

 GoogleFonts

0.42

removeAttr

0.41

igshid

0.41

 CURLOPT

0.41

Kuri

0.40

 térm

0.40

Då

0.40

 máscara

0.40

Activations Density 0.223%

references to programming functions and methods

No Comments

No Known Activations