INDEX

Explanations

formatted strings and code constructs typically associated with programming and configuration in Python

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 MainAxisSize

-0.59

WriteAttribute

-0.58

 autorytatywna

-0.57

\{\\

-0.55

 فريبيس

-0.55

 архивлан

-0.54

Дереккөздер

-0.52

ThroughAttribute

-0.51

Kne

-0.51

 setUser

-0.51

POSITIVE LOGITS

لاعات

0.53

 dafür

0.51

engelsk

0.48

 lâng

0.48

:{}

0.48

 diatas

0.48

 mergeFrom

0.47

suje

0.47

 Catawiki

0.47

kologi

0.46

Activations Density 0.120%

formatted strings and code constructs typically associated with programming and configuration in Python

No Comments

No Known Activations