INDEX

Explanations

mathematical symbols and expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-mlp-65k

Configuration

google/gemma-scope-2b-pt-mlp/layer_4/width_65k/average_l0_66

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.4.hook_mlp_out

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

mtrl

-0.47

cionais

-0.42

ho

-0.40

merie

-0.40

کنون

-0.39

пания

-0.37

minu

-0.36

str

-0.36

'@

-0.35

POSITIVE LOGITS

 CreateTagHelper

0.81

 myſelf

0.79

 للاسماء

0.79

exitRule

0.79

ImageContext

0.78

 Monfieur

0.75

tagHelperRunner

0.75

IUrlHelper

0.75

endphp

0.74

$}}

0.74

Activations Density 0.164%

mathematical symbols and expressions

No Comments

No Known Activations