INDEX

Explanations

uses of articles ('a', 'the'), possessive pronouns ('her', 'their', 'its'), prepositions, and words relating to buildings

oai_token-act-pair · gemini-2.0-flash

housing

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 vérit

-0.84

 ainfi

-0.76

 abbildung

-0.74

 zelve

-0.71

 itſelf

-0.70

 myſelf

-0.68

 auffi

-0.68

gehend

-0.66

felves

-0.66

 theils

-0.64

POSITIVE LOGITS

run

0.62

invokeLater

0.61

 worn

0.59

Run

0.55

Run

0.52

 beat

0.52

лку

0.49

sizeCache

0.49

 newBuilder

0.48

esModule

0.48

Activations Density 2.208%

uses of articles ('a', 'the'), possessive pronouns ('her', 'their', 'its'), prepositions, and words relating to buildings

housing

No Comments

No Known Activations