INDEX

Explanations

actions related to testing or trying new strategies or ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

enterOuterAlt

-0.62

listdir

-0.60

grande

-0.55

Obrázky

-0.53

فاظ

-0.51

writeFieldEnd

-0.51

ngdoc

-0.50

KUN

-0.49

CodeAttribute

-0.49

wst

-0.48

POSITIVE LOGITS

 experiment

1.38

 Experiment

1.36

experiment

1.30

 experiments

1.30

 experimentation

1.27

 experimenting

1.27

Experiment

1.24

 Experiments

1.19

 EXPERIMENT

1.16

 experimented

1.15

Activations Density 0.374%

actions related to testing or trying new strategies or ideas

No Comments

No Known Activations