INDEX

Explanations

key actions or events related to termination or discontinuation

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

preceding a descriptive phrase

np_acts-logits-general · gemini-2.0-flash

ending abruptly

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

뀐

-0.42

뀔

-0.42

DidLoad

-0.39

lessed

-0.37

dek

-0.35

Throughout

-0.35

Einzelnachweise

-0.35

今日も

-0.34

throughout

-0.34

 протяжении

-0.34

POSITIVE LOGITS

 altogether

1.16

 entirely

1.02

 completely

1.00

 abruptly

0.90

 Completely

0.79

 kokona

0.78

Completely

0.78

 prematurely

0.78

 całkow

0.77

 permanently

0.77

Activations Density 0.516%

key actions or events related to termination or discontinuation

preceding a descriptive phrase

ending abruptly

No Comments

No Known Activations