INDEX

Explanations

legal terminology related to liability and connections to software use

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

server configuration

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

enumi

-0.55

Carriera

-0.51

 AssemblyVersion

-0.50

 AssemblyTitle

-0.48

 Gira

-0.47

SerializedName

-0.47

setupUi

-0.46

devamını

-0.46

 فريبيس

-0.45

Manbalar

-0.43

POSITIVE LOGITS

 psycopg

0.74

(_,

0.63

veland

0.61

avro

0.57

 pleaſure

0.55

CDCl

0.54

FileInput

0.53

Produces

0.52

ctest

0.49

=?,

0.47

Activations Density 0.005%

legal terminology related to liability and connections to software use

server configuration

No Comments

No Known Activations