INDEX

Explanations

indicators of logical structure and argumentation within the text

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

Follows punctuation, especially periods and parentheses

np_acts-logits-general · gemini-2.0-flash

end of sentence punctuation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.30.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

BagConstraints

-0.52

 незавершена

-0.48

onedDateTime

-0.46

Népesség

-0.44

 Umständen

-0.42

 Familienname

-0.40

 solches

-0.40

 poupée

-0.40

Huhu

-0.39

czegó

-0.39

POSITIVE LOGITS

Regarding

1.84

 Regarding

1.82

 regarding

1.69

Concerning

1.56

 Concerning

1.55

regarding

1.52

 concerning

1.41

至于

1.32

至於

1.31

 concernant

1.17

Activations Density 0.647%

indicators of logical structure and argumentation within the text

Follows punctuation, especially periods and parentheses

end of sentence punctuation

No Comments

No Known Activations

indicators of logical structure and argumentation within the text

Follows punctuation, especially periods and parentheses

end of sentence punctuation

No Comments

No Known Activations