INDEX

Explanations

phrases that indicate compulsion or obligation

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

yelidikan

-0.89

RTLU

-0.83

Còn

-0.75

SpringRunner

-0.74

 становника

-0.71

@}

-0.69

 jadx

-0.69

StoryboardSegue

-0.69

CWE

-0.69

 gustó

-0.68

POSITIVE LOGITS

 forced

1.75

Forced

1.66

 Forced

1.56

forced

1.42

 forcing

1.33

 compelled

1.27

 Compulsory

1.27

 compulsory

1.21

強制

1.14

 mandatory

1.08

Activations Density 0.183%

phrases that indicate compulsion or obligation

No Comments

No Known Activations