INDEX

Explanations

elements related to parentheses and specific numerical indicators in data contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 ditto

-0.56

cze

-0.53

γμα

-0.49

leby

-0.48

ول

-0.47

û

-0.47

웠

-0.47

stdlib

-0.46

 patienter

-0.46

 màn

-0.46

POSITIVE LOGITS

.*")]

0.85

migrationBuilder

0.80

}();

0.73

NOPQRST

0.72

estero

0.71

Hauptartikel

0.70

 protoimpl

0.69

 pyplot

0.69

UALA

0.68

PhysRevD

0.67

Activations Density 0.231%

elements related to parentheses and specific numerical indicators in data contexts

No Comments

No Known Activations