INDEX

Explanations

the presence of specific markers related to data structures or programming commands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 propOrder

-1.24

SourceChecksum

-1.19

:✨

-0.93

oredCriteria

-0.93

 surla

-0.91

GEBURTSDATUM

-0.89

 AssemblyCulture

-0.89

AndEndTag

-0.88

InjectAttribute

-0.87

TagMode

-0.87

POSITIVE LOGITS

our

0.42

何より

0.41

less

0.39

Ex

0.39

’

0.38

 surtout

0.38

 stesso

0.38

 Pardo

0.37

isdigit

0.37

 itself

0.37

Activations Density 0.434%

the presence of specific markers related to data structures or programming commands

No Comments

No Known Activations