INDEX

Explanations

terms related to properties, locations, and organization within a structured environment

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

DSi transport

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

gonic

-0.46

readystatechange

-0.45

 समीक्षाओं

-0.45

 виправивши

-0.44

+#+#

-0.43

MessageOf

-0.41

]")]

-0.41

drawSprites

-0.41

BRIT

-0.40

dafx

-0.40

POSITIVE LOGITS

).__

0.42

 متعلقه

0.42

OLEAN

0.42

0.40

astéro

0.39

 egress

0.38

öl

0.37

thenReturn

0.36

ništ

0.36

 Taktlose

0.35

Activations Density 0.001%

terms related to properties, locations, and organization within a structured environment

DSi transport

No Comments

No Known Activations