INDEX

Explanations

words related to keywords and keyword research in digital marketing

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

Ness

-0.83

-0.79

tagHelper

-0.79

-0.73

usermodel

-0.73

porta

-0.72

 Maxine

-0.72

 Harding

-0.71

 Ness

-0.70

POSITIVE LOGITS

 keywords

1.04

 raiſ

0.91

 Keyword

0.91

keyword

0.90

 uſed

0.89

 themſelves

0.85

 Keywords

0.85

ség

0.84

 vectorielle

0.84

 whoſe

0.84

Activations Density 0.146%

words related to keywords and keyword research in digital marketing

No Comments

No Known Activations