INDEX

Explanations

terms related to options or choices in various contexts

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

Options

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 ब्रेकडाउन

-0.48

InBackground

-0.46

endforeach

-0.45

zarchiwizowane

-0.44

Guillaume

-0.43

BaseAdapter

-0.43

GitHub

-0.42

 Schä

-0.42

unhofer

-0.39

Become

-0.39

POSITIVE LOGITS

Options

2.73

 Options

1.91

OPTIONS

1.56

 OPTIONS

1.47

options

1.40

getOptions

1.37

setOptions

1.23

Opts

1.10

 Optionen

1.09

Opciones

1.09

Activations Density 0.004%

terms related to options or choices in various contexts

Options

No Comments

No Known Activations