INDEX

Explanations

instances of time references, particularly the word "years" and its variations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

\{\\

-0.93

ConstraintMaker

-0.86

 McClellan

-0.81

piecz

-0.79

 Driscoll

-0.76

anganronpa

-0.76

SPJ

-0.76

最快更新

-0.75

 policiais

-0.74

dumps

-0.73

POSITIVE LOGITS

 years

2.25

 Years

1.86

years

1.78

Years

1.74

 year

1.71

 YEARS

1.69

year

1.51

 Year

1.50

 años

1.49

 YEAR

1.45

Activations Density 0.087%

instances of time references, particularly the word "years" and its variations

No Comments

No Known Activations