INDEX

Explanations

programming-related instructions and function calls

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

ModelSerializer

-0.60

 насељу

-0.56

ListItemIcon

-0.54

DeleteBehavior

-0.54

UserScript

-0.53

favorited

-0.53

bkz

-0.53

RUnlock

-0.53

Uninitialized

-0.52

 spite

-0.51

POSITIVE LOGITS

 AssemblyCulture

0.72

 yourself

0.61

 autorytatywna

0.61

 your

0.52

ITURE

0.51

 GlobalKey

0.50

畳

0.50

 lenker

0.49

Personensuche

0.47

Bibliograf

0.47

Activations Density 0.198%

programming-related instructions and function calls

No Comments

No Known Activations