INDEX

Explanations

terms related to roles, authorship, and organizational structure within a framework

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 Мексичка

-0.77

 GenerationType

-0.77

AddTagHelper

-0.76

 }}$}

-0.74

UnusedPrivate

-0.72

KommentareTeilen

-0.71

TagMode

-0.70

_$

-0.70

///</

-0.69

enumii

-0.69

POSITIVE LOGITS

 sponsor

0.80

 creator

0.75

 owner

0.74

 creators

0.69

作者

0.67

 operator

0.67

 opérateur

0.67

 manufacturer

0.65

 sponsors

0.64

 OWNER

0.64

Activations Density 0.471%

terms related to roles, authorship, and organizational structure within a framework

No Comments

No Known Activations