INDEX

Explanations

actions related to the process of performing tasks or operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 kaynağından

-0.75

 TextInputType

-0.72

onAttach

-0.64

 engraçadas

-0.63

mybatisplus

-0.63

AsUp

-0.62

AccessorTable

-0.62

Expansion

-0.61

 Expansion

-0.60

 Territor

-0.60

POSITIVE LOGITS

 performed

3.41

 perform

3.32

 performing

3.11

 Perform

3.03

 performs

3.03

Perform

2.91

 Performed

2.87

performed

2.79

perform

2.77

 PERFORM

2.77

Activations Density 0.143%

actions related to the process of performing tasks or operations

No Comments

No Known Activations