INDEX

Explanations

sequences of characters often found in programming syntax or error messages

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

TRIBUN

-0.58

])))

-0.57

 Gelder

-0.56

tableFuture

-0.55

 signaling

-0.54

 league

-0.53

]();

-0.53

strateg

-0.52

TargetException

-0.52

VIAF

-0.51

POSITIVE LOGITS

(_,

0.75

(_,

0.72

 بيها

0.71

batore

0.59

mentaux

0.59

 ExecuteAsync

0.57

EndInit

0.56

moin

0.54

:",

0.54

ômes

0.53

Activations Density 0.405%

sequences of characters often found in programming syntax or error messages

No Comments

No Known Activations