INDEX

Explanations

phrases related to violent actions or crimes

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

 externes

-0.57

rrggbb

-0.54

thâu

-0.53

hyrchwyd

-0.53

 dAtA

-0.53

ględ

-0.52

Obras

-0.52

inars

-0.52

spira

-0.52

AddColumn

-0.52

POSITIVE LOGITS

 politely

0.69

 polite

0.65

исленность

0.60

 AssemblyProduct

0.59

 threatening

0.58

 unfriendly

0.56

 rude

0.56

 dialogue

0.55

 rudely

0.55

 hostility

0.54

Activations Density 0.258%

phrases related to violent actions or crimes

No Comments

No Known Activations