INDEX

Explanations

occurrences of code or formatting commands in a document

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

 ModelExpression

-0.89

 itſelf

-0.83

 myſelf

-0.77

AsUp

-0.72

SourceChecksum

-0.72

LabelTagHelper

-0.69

 himſelf

-0.67

}],

-0.66

}>;

-0.64

 Sarm

-0.64

POSITIVE LOGITS

0.87

usepackage

0.76

{~

0.63

níky

0.60

ndorf

0.58

rika

0.57

gewiesen

0.56

 vues

0.55

chero

0.54

{-

0.51

Activations Density 0.032%

occurrences of code or formatting commands in a document

No Comments

No Known Activations