INDEX

Explanations

interrogative phrases and references to questioning or inquiries related to individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

MockBean

-0.65

WebElementEntity

-0.65

centralwidget

-0.64

rrggbb

-0.63

hObject

-0.60

 Италијани

-0.56

 Públicas

-0.56

 INTERESAR

-0.56

 AppColors

-0.55

JsonHelper

-0.54

POSITIVE LOGITS

 what

0.96

 questions

0.91

 about

0.88

why

0.85

 question

0.76

how

0.75

 whether

0.72

what

0.71

EndContext

0.69

 Question

0.67

Activations Density 0.089%

interrogative phrases and references to questioning or inquiries related to individuals

No Comments

No Known Activations