INDEX

Explanations

words and phrases indicating generalization or typicality

oai_token-act-pair · gemini-2.0-flash

always/so

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

<bos>

-1.40

MigrationBuilder

-0.79

InstrumentedTest

-0.79

 GenerationType

-0.77

LookAnd

-0.76

InitVars

-0.76

NameInMap

-0.74

IUrlHelper

-0.70

RTLD

-0.69

 gyhoeddwyd

-0.69

POSITIVE LOGITS

 contemporain

0.65

 pylint

0.60

 compromis

0.57

revet

0.54

 Finalmente

0.54

 biologique

0.53

 contemporaine

0.53

 clot

0.52

Obl

0.52

 fewest

0.52

Activations Density 0.638%

words and phrases indicating generalization or typicality

always/so

No Comments

No Known Activations