INDEX

Explanations

terms related to movies or filmmaking

oai_token-act-pair · gemini-2.0-flash

film-related terms

np_token-act-pair-logits · gpt-4o-mini

film/movie

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

المكان

-0.61

 становника

-0.60

migrationBuilder

-0.54

parsedMessage

-0.53

出版年

-0.52

 bParam

-0.52

AutoScaleMode

-0.51



-0.51

 film

-0.50

bukkit

-0.49

POSITIVE LOGITS

 critic

0.66

 iconTwitter

0.63

IndentedString

0.57

 critics

0.56

 digitally

0.54

inobu

0.52

 Drapeau

0.51

 Dorsal

0.51

[])

0.50

embatan

0.50

Activations Density 1.591%

terms related to movies or filmmaking

film-related terms

film/movie

No Comments

No Known Activations