INDEX

Explanations

actions related to running scripts or executing commands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

rrggbb

-0.67

 cref

-0.54

PropertyGroup

-0.53

jkl

-0.52

 Buckle

-0.49

styleable

-0.48

 recev

-0.47

atory

-0.47

 Reusable

-0.47

 profondément

-0.47

POSITIVE LOGITS

 runs

1.57

run

1.52

 running

1.42

ran

1.37

runs

1.35

 Runs

1.32

RUN

1.29

Running

1.27

Runs

1.27

 Running

1.26

Activations Density 0.175%

actions related to running scripts or executing commands

No Comments

No Known Activations