INDEX

Explanations

terms related to tracking or monitoring

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

LoadScene

-0.70

usammen

-0.60

 SEDS

-0.57

setScene

-0.56

ButtonStyle

-0.56

 Dame

-0.55

/\.

-0.55

jäh

-0.54

 /\.(

-0.54

voorbeeld

-0.54

POSITIVE LOGITS

 tracking

1.22

 Tracking

1.21

 tracker

1.15

 Tracker

1.10

Tracking

1.06

tracking

1.06

 trackers

1.04

tracker

1.04

Tracker

0.90

IContainer

0.88

Activations Density 0.071%

terms related to tracking or monitoring

No Comments

No Known Activations