INDEX

Explanations

key roles and responsibilities in various professional contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

article or pronoun followed by new concept

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

It detects sentence-level grammatical markers that open factual statements—auxiliary/main verbs like "has/is/receives/was" and nearby determiners/articles such as "a" and "an."

oai_token-act-pair · gpt-5-mini

Triggered by @vetterc0

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

Jereo

-0.30

ES

-0.28

 gynhyrchwyd

-0.28

 tantôt

-0.26

 felling

-0.26

โคร

-0.25

Moreover

-0.25

statechange

-0.25

 última

-0.25

 временем

-0.25

POSITIVE LOGITS

 queſta

0.75

دانشنامهٔ

0.65

 témoig

0.65

 EconPapers

0.65

<unused14>

0.63

<unused8>

0.63

<unused41>

0.63

<unused74>

0.63

<unused3>

0.63

<unused21>

0.63

Activations Density 0.402%

key roles and responsibilities in various professional contexts

article or pronoun followed by new concept

It detects sentence-level grammatical markers that open factual statements—auxiliary/main verbs like "has/is/receives/was" and nearby determiners/articles such as "a" and "an."

No Known Activations

key roles and responsibilities in various professional contexts

article or pronoun followed by new concept

It detects sentence-level grammatical markers that open factual statements—auxiliary/main verbs like "has/is/receives/was" and nearby determiners/articles such as "a" and "an."

No Known Activations