INDEX

Explanations

actions involving violence or aggression

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

classmethod

-0.55

 sentiers

-0.54

열

-0.51

adhé

-0.51

queryInterface

-0.50

 hendes

-0.49

Forward

-0.48

דיה

-0.48

pstead

-0.48

 possano

-0.48

POSITIVE LOGITS

 propOrder

0.77

complexContent

0.73

 بيها

0.68

HasIndex

0.65

GOTREF

0.64

 them

0.60

onAttach

0.58

updateOne

0.57

uxxxx

0.56

FieldBuilder

0.56

Activations Density 0.546%

actions involving violence or aggression

No Comments

No Known Activations