INDEX

Explanations

terms related to peaks in statistical distributions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

.........

-0.72

so

-0.65

</strong>

-0.62

-0.61

 fact

-0.60

...

-0.59

was

-0.58

Kot

-0.58

MathML

-0.58

POSITIVE LOGITS

 peaks

1.67

 Peak

1.62

 PEAK

1.62

 Peaks

1.58

 peak

1.55

Peak

1.54

peak

1.40

peaks

1.36

 peaking

1.23

 peaked

1.22

Activations Density 0.125%

terms related to peaks in statistical distributions

No Comments

No Known Activations