INDEX

Explanations

specific references to personal experiences and claims

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

existence and state

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

the neuron detects finite (conjugated) verbs — i.e., main and auxiliary verbs showing tense/person (states or actions).

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

Not in Any Lists

No Comments

Negative Logits

moiselle

-0.38

 sempat

-0.37

もありました

-0.37

ProgressHUD

-0.36

ASG

-0.36

Predecesor

-0.35

Apro

-0.35

vertisement

-0.33

cg

-0.33

TaskId

-0.33

POSITIVE LOGITS

addContainerGap

0.60

 jsPsych

0.57

.*")]

0.52

astéro

0.51

Cyfarwyddwr

0.51

 فريبيس

0.50

 الحره

0.49

 بيها

0.48

الحياه

0.47

 теперь

0.47

Activations Density 1.947%

specific references to personal experiences and claims

existence and state

the neuron detects finite (conjugated) verbs — i.e., main and auxiliary verbs showing tense/person (states or actions).

No Comments

No Known Activations

specific references to personal experiences and claims

existence and state

the neuron detects finite (conjugated) verbs — i.e., main and auxiliary verbs showing tense/person (states or actions).

No Comments

No Known Activations