INDEX

Explanations

terms related to mounting mechanisms and configurations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

addGap

-0.73

enumi

-0.67

 Sarg

-0.66

Ucraina

-0.65

enumii

-0.64

nergy

-0.61

onoi

-0.59

 Allahabad

-0.57

bbean

-0.56

Спасылкі

-0.56

POSITIVE LOGITS

 mount

2.42

 mounts

2.40

 Mount

2.37

Mount

2.32

 Mounts

2.31

 MOUNT

2.30

mount

2.14

MOUNT

2.12

 mounted

2.09

mounted

2.01

Activations Density 0.081%

terms related to mounting mechanisms and configurations

No Comments

No Known Activations