INDEX

Explanations

code snippets related to data processing and manipulation tasks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

一头

-0.72

一座

-0.71

一支

-0.68

一场

-0.67

一種

-0.67

一張

-0.67

一隻

-0.66

Hauptartikel

-0.66

 صوتيه

-0.66

RectangleBorder

-0.66

POSITIVE LOGITS

len

0.82

len

0.71

 disambiguazione

0.54

Len

0.52

NEA

0.48

 vacacionales

0.48

 inconnu

0.46

Viitteet

0.46

IVEREF

0.45

leno

0.44

Activations Density 0.051%

code snippets related to data processing and manipulation tasks

No Comments

No Known Activations