INDEX

Explanations

temporal phrases indicating sequences of events or changes over time

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

after events or durations

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

 OMITTED

-0.45

 omitted

-0.45

 berhenti

-0.44

 retraso

-0.44

 disparu

-0.44

 egli

-0.43

 égard

-0.41

 infatti

-0.41

iNdEx

-0.41

 asimismo

-0.40

POSITIVE LOGITS

 ब्रेकडाउन

0.62

CodeAnalysis

0.48

 GetComponent

0.47

TestingModule

0.45

trop

0.44

 useAuth

0.44

 constat

0.43

KommentareTeilen

0.42

 unsatisfactory

0.41

 maximum

0.40

Activations Density 0.040%

temporal phrases indicating sequences of events or changes over time

after events or durations

No Comments

No Known Activations