INDEX

Explanations

specific identifiers related to unnamed sources or classifications in various contexts

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

meaning "unnamed" or "anonymous"

np_acts-logits-general · gemini-2.0-flash

unnamed, anonymous, nameless

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 viewDidLoad

-0.42

fitriones

-0.40

Mic

-0.37

 grades

-0.36

principalColumn

-0.34

jme

-0.33

:+:

-0.33

sidemargin

-0.33

quième

-0.31

 đốc

-0.31

POSITIVE LOGITS

 unnamed

1.16

 nameless

1.07

 anonymous

0.96

 unidentified

0.94

Unnamed

0.91

unnamed

0.89

anonymous

0.82

 unknown

0.81

Anonymous

0.80

 Anonymous

0.80

Activations Density 0.812%

specific identifiers related to unnamed sources or classifications in various contexts

meaning "unnamed" or "anonymous"

unnamed, anonymous, nameless

No Comments

No Known Activations