INDEX

Explanations

references to movies and television

oai_token-act-pair · gemini-2.0-flash

mixed language entries or code snippets

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

movie reviews

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

юрпри

-0.44

ả

-0.44

ilog

-0.43

setVerticalGroup

-0.43

=*/

-0.42

modo

-0.42

 ри

-0.42

 bing

-0.41

nth

-0.40

atina

-0.40

POSITIVE LOGITS

 للمعارف

0.82

 שוליים

0.78

Espèce

0.76

 وتسجيلات

0.70

__':

0.70

 <=",

0.70

 >=",

0.69

 AssemblyTitle

0.68

ResumeLayout

0.65

 onCancelled

0.64

Activations Density 0.194%

references to movies and television

mixed language entries or code snippets

movie reviews

No Comments

No Known Activations