INDEX

Explanations

references to abilities, skills, or characteristics related to activities or tasks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 שונים

-0.86

parsedMessage

-0.84

 חיצוניים

-0.79

 quelli

-0.75

 suivants

-0.74

 אחרים

-0.74

ônicos

-0.72

 utilizzati

-0.71

éricos

-0.70

Eles

-0.70

POSITIVE LOGITS

she

0.64

étricas

0.58

she

0.57

ógicas

0.54

彼女は

0.53

 Одна

0.53

ólicas

0.52

She

0.51

ográficas

0.49

 herself

0.49

Activations Density 0.153%

references to abilities, skills, or characteristics related to activities or tasks

No Comments

No Known Activations