INDEX

Explanations

terms related to documentation, validation, and formal processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

SPATH

-0.48

але

-0.42

andExpect

-0.42

طق

-0.41

 parent

-0.40

OnError

-0.39

 initWith

-0.39

 Path

-0.38

ままで

-0.38

hasPermission

-0.38

POSITIVE LOGITS

GEBURTSDATUM

0.89

 gynnwys

0.86

addCriterion

0.85

 &___

0.83

RenderAtEndOf

0.82

pushFollow

0.76

 otomatig

0.73

Carriera

0.73

 disambiguazione

0.71

Personendaten

0.71

Activations Density 0.212%

terms related to documentation, validation, and formal processes

No Comments

No Known Activations