INDEX

Explanations

proper names and locations

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

Spartan history

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

afficheront

-0.52

 intptr

-0.45

CppCodeGen

-0.43

期刊论文

-0.42

anglès

-0.41

IntoConstraints

-0.41

iettivo

-0.40

 CURIAM

-0.39

 استنادى

-0.39

POSITIVE LOGITS

 Spartan

0.75

 Sparta

0.73

Spartan

0.69

Sparta

0.64

 Spartans

0.64

 Spart

0.60

 spartan

0.55

 spart

0.48

 Spar

0.47

DataSetChanged

0.46

Activations Density 0.028%

proper names and locations

Spartan history

No Comments

No Known Activations

proper names and locations

Spartan history

No Comments

No Known Activations