INDEX

Explanations

references to properties and definitions in a structured data schema

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

references and following punctuation

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

Out

-0.34

rungsseite

-0.34

Ing

-0.33

Out

-0.33

Dra

-0.30

Access

-0.30

Dra

-0.30

dra

-0.29

ertes

-0.29

TagHelper

-0.29

POSITIVE LOGITS

ref

1.07

ref

0.89

MLLoader

0.85

REF

0.77

httphttps

0.74

REF

0.71

 pinulongan

0.70

Ref

0.69

OGND

0.66

 ProtoMessage

0.65

Activations Density 0.031%

references to properties and definitions in a structured data schema

references and following punctuation

No Comments

No Known Activations

references to properties and definitions in a structured data schema

references and following punctuation

No Comments

No Known Activations