INDEX

Explanations

modal verbs indicating ability or possibility

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

ability or possibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

Autoritní

-0.49

decide

-0.47

paravant

-0.43

قایناق‌لار

-0.41

]}"

-0.40

 decidir

-0.40

decided

-0.40

 aDecoder

-0.40

decisions

-0.40

rimas

-0.39

POSITIVE LOGITS

 doable

0.59

 workable

0.59

 succeed

0.58

 achievable

0.57

 successfully

0.57

 profitably

0.54

 safely

0.53

 successful

0.53

 viable

0.53

 feasible

0.53

Activations Density 0.068%

modal verbs indicating ability or possibility

ability or possibility

No Comments

No Known Activations