INDEX

Explanations

terms related to mathematical or scientific notation

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.6.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

 infusion

-0.41

aus

-0.41

 eche

-0.40

 ausge

-0.40

dine

-0.39

VEN

-0.39

 inspector

-0.39

ibig

-0.39

 MACH

-0.39

 Virgin

-0.39

POSITIVE LOGITS

 Roskov

0.70

AccessorTable

0.65

CppMethod

0.60

 disambiguazione

0.56

 للمعارف

0.56

脚注の使い方

0.52

 iParam

0.52

pexpr

0.51

protoimpl

0.51

цездатний

0.51

Activations Density 0.012%

terms related to mathematical or scientific notation

No Comments

No Known Activations