INDEX

Explanations

phrases related to prevention or stopping actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/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.19.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

 muualla

-0.71

ItemBackground

-0.70

 ComVisible

-0.66

 للاسماء

-0.64

IsMutable

-0.64

sonian

-0.64

 Infórmanos

-0.63

rungsseite

-0.61

 autorytatywna

-0.61

 Taktlose

-0.60

POSITIVE LOGITS

 from

1.07

 access

0.77

from

0.70

access

0.65

 prevent

0.65

 Zugriff

0.63

 progress

0.62

 FROM

0.61

 Prevent

0.61

 от

0.61

Activations Density 0.245%

phrases related to prevention or stopping actions

No Comments

No Known Activations