INDEX

Explanations

terms related to detection and monitoring events or conditions

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

InputBorder

-0.66

$__

-0.60

 Humphreys

-0.59

TypedDataSet

-0.56

freopen

-0.56

 pymongo

-0.55

sequelize

-0.55

CreateMap

-0.53

⬇️

-0.52

 Okla

-0.52

POSITIVE LOGITS

 detect

1.13

 detected

1.01

 detects

1.00

 Detect

0.95

 notice

0.95

Detect

0.88

出版年

0.86

 detecting

0.86

 détect

0.83

detected

0.81

Activations Density 0.111%

terms related to detection and monitoring events or conditions

No Comments

No Known Activations