INDEX

Explanations

uses of "going to" as well as some seemingly random words like "guy"

oai_token-act-pair · gemini-2.0-flash

future tense/intent

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 really

-0.62

 gotta

-0.62

 gonna

-0.59

 Gonna

-0.59

lot

-0.54

 GONNA

-0.53

 lotta

-0.50

got

-0.50

Gonna

-0.50

 awfully

-0.50

POSITIVE LOGITS

 ویکی‌پدیا

0.91

protoimpl

0.77

adpleegd

0.75

oa̍t

0.74

 mergeFrom

0.72

الدراسه

0.71

onAttach

0.71

ocino

0.70

 незавершена

0.68

Personensuche

0.68

Activations Density 3.300%

uses of "going to" as well as some seemingly random words like "guy"

future tense/intent

No Comments

No Known Activations