INDEX

Explanations

names and specific identifiers of individuals and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 EconPapers

-0.89

AndroidJUnit

-0.82

DockStyle

-0.81

########.

-0.80

出版年

-0.79

 houſe

-0.77

ArrowToggle

-0.77

 Reſ

-0.75

Rhestr

-0.75

 ſta

-0.74

POSITIVE LOGITS

dicionado

0.46

VersionUID

0.45

Jr

0.45

0.44

who

0.41

 revisor

0.41

︎

0.41

gheny

0.40

),

0.40

Activations Density 0.217%

names and specific identifiers of individuals and entities

No Comments

No Known Activations

names and specific identifiers of individuals and entities

No Comments

No Known Activations