INDEX

Explanations

quoted strings or string literals

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

atorio

-0.53

formatie

-0.50

 См

-0.49

közi

-0.49

éton

-0.48

 weary

-0.48

hiz

-0.47

ToMany

-0.47

igung

-0.47

atorios

-0.47

POSITIVE LOGITS

/**

0.95

/*

0.93

 resourceCulture

0.86

:✨

0.84

endphp

0.76

_("

0.73

 kasarigan

0.72

<bos>

0.70

Personendaten

0.69

__((

0.68

Activations Density 0.124%

quoted strings or string literals

No Comments

No Known Activations