INDEX

Explanations

mentions of "year" in various contexts

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

yearly events

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

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

RTEE

-0.47

onomía

-0.45

 eivät

-0.44

WriteTagHelper

-0.43

 ceased

-0.42

addPreferred

-0.42

 plutôt

-0.42

ösung

-0.42

arangay

-0.41

 huéspedes

-0.40

POSITIVE LOGITS

 annually

1.04

 yearly

0.96

 annual

0.94

Annual

0.89

annual

0.87

 Annual

0.85

 anual

0.84

 Yearly

0.81

yearly

0.81

 jährlich

0.80

Activations Density 0.014%

mentions of "year" in various contexts

yearly events

No Comments

No Known Activations