INDEX

Explanations

phrases indicating urgency or commands related to taking action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 angen

-0.54

WIG

-0.54

 createSlice

-0.46

inc

-0.44

},{

-0.43

tid

-0.43

idió

-0.42

Continuous

-0.42

cydow

-0.42

 continuous

-0.42

POSITIVE LOGITS

 yourself

1.09

 yourselves

1.04

 Yourself

0.83

yourself

0.83

 thyself

0.77

 YOURSELF

0.74

 HttpNotFound

0.74

 initComponents

0.74

 your

0.72

Yourself

0.69

Activations Density 0.189%

phrases indicating urgency or commands related to taking action

No Comments

No Known Activations