INDEX

Explanations

occurrences of variables, specifically those that start with the dollar sign ($)

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

[]){

-0.70

 Италијани

-0.66

)++;

-0.66

InitVars

-0.65

 otomatig

-0.64

'}),

-0.64

 ModelRenderer

-0.64

UnusedPrivate

-0.63

ArgumentParser

-0.62

:]:

-0.62

POSITIVE LOGITS

0.61

|=

0.60

 gomma

0.59

󠁢

0.58

 olduk

0.58

 hjel

0.58

 kics

0.55

 eredeti

0.55

RuleContext

0.54

 hyö

0.54

Activations Density 0.021%

occurrences of variables, specifically those that start with the dollar sign ($)

No Comments

No Known Activations