INDEX

Explanations

references to the word "this"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 McGovern

-0.78

)|^{

-0.71

windowFixed

-0.71

+:+

-0.69

WebElementEntity

-0.67

Diwedd

-0.66

illips

-0.66

########.

-0.65

afficheront

-0.64

()]);

-0.64

POSITIVE LOGITS

 selves

0.79

 Myself

0.78

 ourselves

0.78

myself

0.77

 throm

0.76

Myself

0.75

 istruzioni

0.71

 myself

0.70

Mucha

0.68

enumi

0.66

Activations Density 0.024%

references to the word "this"

No Comments

No Known Activations