INDEX

Explanations

terms related to early actions and decisions

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

early decision, early publication, early mover

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

 snippetHide

-0.38

romolecules

-0.35

irci

-0.35

isert

-0.33

namentales

-0.32

hpur

-0.32

nsic

-0.32

Statistiche

-0.32

 Dire

-0.32

opathology

-0.32

POSITIVE LOGITS

early

0.89

Early

0.86

 EARLY

0.80

 Early

0.77

 early

0.77

EARLY

0.74

早

0.66

 temprana

0.65

 premature

0.63

 temprano

0.60

Activations Density 0.101%

terms related to early actions and decisions

early decision, early publication, early mover

No Comments

No Known Activations