INDEX

Explanations

words that occur frequently within a specific, limited context.

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rrggbb

-0.59

zzleHttp

-0.52

shortcuts

-0.45

Bioaccumulative

-0.42

ίδ

-0.42

 createSprite

-0.40

IANT

-0.40

ran

-0.39

 Werner

-0.39

pro

-0.39

POSITIVE LOGITS

 NSCoder

0.66

EndContext

0.65

AddTagHelper

0.65

 Normdatei

0.65

adpleegd

0.64

EndInit

0.62

ArgsConstructor

0.61

SourceChecksum

0.61

ьаж

0.59

clyde

0.57

Activations Density 0.740%

words that occur frequently within a specific, limited context.

No Comments

No Known Activations