INDEX

Explanations

references to tags and tagging processes in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

atoires

-0.69

-0.66

 تانيه

-0.64

Portail

-0.62

ToDecimal

-0.62

wright

-0.60

 cradle

-0.60

exprimer

-0.60

mpy

-0.59

 Soleil

-0.59

POSITIVE LOGITS

 tags

1.59

tag

1.56

Tag

1.49

tags

1.44

TAG

1.39

 Tags

1.36

Tag

1.33

 TAGS

1.22

tag

1.19

WithTag

1.18

Activations Density 0.084%

references to tags and tagging processes in a text

No Comments

No Known Activations