INDEX

Explanations

references to auditory experiences or sounds

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

ulti

-0.55

 blind

-0.55

 aveug

-0.53

WebControls

-0.53

big

-0.53

importe

-0.51

olved

-0.49

 heads

-0.49

WebServlet

-0.48

madol

-0.48

POSITIVE LOGITS

 sounded

0.77

ToolStripButton

0.64

AsUp

0.64

DSG

0.64

RemoveField

0.63

derung

0.62

 jenner

0.62

 AppCompatTheme

0.62

 від

0.61

 smells

0.60

Activations Density 0.109%

references to auditory experiences or sounds

No Comments

No Known Activations