INDEX

Explanations

references to specific programming libraries and frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

 pubblici

-0.57

üch

-0.53

 demonios

-0.52

Έ

-0.51

許

-0.50

 aras

-0.49

 Cortés

-0.49

 uite

-0.49

 chiaramente

-0.49

端

-0.48

POSITIVE LOGITS

CodeDom

4.89

 оригіналу

1.11

الإنجليزية

1.11

Geplaatst

1.09

 MainAxisSize

0.99

GeneratedCode

0.91

 الاطلاع

0.89

 nakalista

0.86

CWE

0.82

XmlAccessType

0.82

Activations Density 0.009%

references to specific programming libraries and frameworks

No Comments

No Known Activations