INDEX

Explanations

mathematical comparisons and evaluations related to values and their relationships

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

values, closest, biggest, smallest

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

OGND

-0.51

*/),

-0.48

GEBURTSDATUM

-0.45

+:+

-0.44

expandindo

-0.44

 ['./

-0.42

')):

-0.41

Hochspringen

-0.41

\]

-0.40

"):

-0.40

POSITIVE LOGITS

чат

0.45

umenter

0.45

 Sympathi

0.44

höhung

0.44

 המת

0.44

itzt

0.43

 atitude

0.42

icator

0.42

Etimología

0.42

 tactic

0.41

Activations Density 0.127%

mathematical comparisons and evaluations related to values and their relationships

values, closest, biggest, smallest

No Comments

No Known Activations