INDEX

Explanations

negative indicators and specific group classifications within scientific contexts

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

species-specific

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

InitVars

-0.47

揄

-0.46

 Wortes

-0.37

 Gild

-0.37

MoveNext

-0.37

Jeografia

-0.36

министра

-0.35

πη

-0.34

 accord

-0.34

 insult

-0.34

POSITIVE LOGITS

клопе

0.71

 Roskov

0.55

 pinulongan

0.50

 Paglinawan

0.49

 oprot

0.48

Species

0.46

 وتسجيلات

0.43

 citoy

0.43

orcid

0.43

 species

0.42

Activations Density 0.000%

negative indicators and specific group classifications within scientific contexts

species-specific

No Comments

No Known Activations