INDEX

Explanations

terms related to the concept of cancellation or errors in communication

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

cancel, canceled, cancellation

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

 desafíos

-0.40

 relève

-0.40

 suficientemente

-0.38

 retos

-0.38

 logros

-0.37

 défis

-0.37

Rohy

-0.36

 obtend

-0.36

twimg

-0.36

볼

-0.36

POSITIVE LOGITS

 cancelled

1.21

 cancellation

1.20

 cancelling

1.20

 canceled

1.18

 canceling

1.16

 Cancelled

1.13

Cancelled

1.13

cancelled

1.12

 cancellations

1.11

 cancel

1.10

Activations Density 0.028%

terms related to the concept of cancellation or errors in communication

cancel, canceled, cancellation

No Comments

No Known Activations