INDEX

Explanations

references to murder

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 évit

-0.80

 stället

-0.73

లాలు

-0.70

 hindurch

-0.67

antaranya

-0.66

 ReactDOM

-0.66

 föres

-0.66

forName

-0.65

thâu

-0.65

 antemano

-0.64

POSITIVE LOGITS

Interaction

0.84

 interaction

0.78

 murder

0.77

 Murder

0.75

Murder

0.74

 interactive

0.74

 interak

0.73

interaction

0.72

 interactions

0.71

msgTypes

0.69

Activations Density 0.160%

references to murder

No Comments

No Known Activations