INDEX

Explanations

underscores in words or phrases

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

function definition body

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

MLLoader

-1.05

RegistryLite

-0.95

 queſta

-0.94

ſelf

-0.92

󠁢

-0.92

ſelves

-0.91

featureID

-0.88

 AssemblyCompany

-0.85

principalColumn

-0.83

 Normdatei

-0.83

POSITIVE LOGITS

0.40

ing

0.39

0.38

0.36

0.35

liche

0.35

is

0.35

Activations Density 0.067%

underscores in words or phrases

function definition body

No Comments

No Known Activations