INDEX

Explanations

punctuations and structure in text

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

Follows a period

np_acts-logits-general · gemini-2.0-flash

starts of new sentences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 trône

-0.49

 propOrder

-0.43

anuts

-0.41

resistance

-0.41

Literatur

-0.40

secre

-0.40

 carve

-0.40

 rowspan

-0.40

getreten

-0.40

aternity

-0.39

POSITIVE LOGITS

PMailer

0.40

databind

0.39

 ApiException

0.37

Ekster

0.36

~*~

0.36

evos

0.36

ALREADY

0.35

ERVIS

0.35

 Chwiliwch

0.34

endmodule

0.34

Activations Density 0.373%

punctuations and structure in text

Follows a period

starts of new sentences

No Comments

No Known Activations