INDEX

Explanations

references to the optimization and management of digital resources or capabilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 OMIT

-0.64

findpost

-0.63

PYX

-0.62

 nahilalakip

-0.60

AndEndTag

-0.56

verifyException

-0.56

::*;

-0.53

 Paglinawan

-0.53

 ExecuteAsync

-0.52

 كومونز

-0.52

POSITIVE LOGITS

 further

3.10

further

2.83

Further

2.47

 Further

2.44

 FURTHER

2.39

 ytterligare

2.26

 weitere

2.17

 additional

2.12

 weiteren

2.10

FURTHER

2.09

Activations Density 1.429%

references to the optimization and management of digital resources or capabilities

No Comments

No Known Activations