INDEX

Explanations

terms related to design and optimization in technology and engineering

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_131k/average_l0_101

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.23.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

 telefónica

-0.50

 reciclado

-0.48

aarrggbb

-0.48

 iprot

-0.48

 fasilitas

-0.47

 ""],

-0.46

 initComponents

-0.46

 času

-0.45

ไหน

-0.45

hematics

-0.45

POSITIVE LOGITS

 specific

0.44

 ausz

0.43

Specifically

0.41

Specific

0.41

 specifically

0.40

 Moul

0.40

 &___

0.40

kep

0.40

 Specific

0.39

coroutines

0.39

Activations Density 0.155%

terms related to design and optimization in technology and engineering

No Comments

No Known Activations