INDEX

Explanations

various forms of the word "add" and related functions in code

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 surla

-0.97

*/].

-0.88

findpost

-0.87

 initComponents

-0.87

archiviato

-0.84

 ***/

-0.82

OGND

-0.82

 glyphicon

-0.82

 <<<<<<<<<<<<<<

-0.81

QMetaType

-0.81

POSITIVE LOGITS

Add

1.76

Add

1.72

ADD

1.53

add

1.51

ADD

1.49

add

1.44

 Adds

1.31

 adds

1.25

 Addis

1.11

Adder

1.11

Activations Density 0.056%

various forms of the word "add" and related functions in code

No Comments

No Known Activations