INDEX

Explanations

references to data visualization and statistical results in scientific context

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

Comes before figure/table references

np_acts-logits-general · gemini-2.0-flash

following punctuation, introducing clauses

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SequentialGroup

-0.81

withIdentifier

-0.75

endpush

-0.73

mybatisplus

-0.72

principalTable

-0.71

Tembelea

-0.70

ReusableCell

-0.70

ItemBackground

-0.66

المناصب

-0.66

----</

-0.65

POSITIVE LOGITS

 notice

1.57

 Notice

1.56

Notice

1.50

notice

1.47

 note

1.21

 clearly

1.20

Clearly

1.17

 Clearly

1.15

 noticed

1.11

clearly

1.09

Activations Density 0.772%

references to data visualization and statistical results in scientific context

Comes before figure/table references

following punctuation, introducing clauses

No Comments

No Known Activations