INDEX

Explanations

phrases indicating ongoing or past actions or states of being

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

osa

-0.47

 zamanda

-0.47

ly

-0.45

 comodo

-0.45

 attiv

-0.44

 nonché

-0.44

 vůbec

-0.44

 Tutu

-0.43

 emblema

-0.42

どき

-0.42

POSITIVE LOGITS

=$?

0.89

 '\\;'

0.77

mpotent

0.72

 ujednoznacz

0.71

utze

0.71

Bew

0.70

DatabaseError

0.67

PMailer

0.66

 تانيه

0.66

Czytaj

0.65

Activations Density 0.542%

phrases indicating ongoing or past actions or states of being

No Comments

No Known Activations