INDEX

Explanations

instances of the word "restore" and its variations, indicating a focus on recovery or regaining something that has been lost

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 flexible

-0.41

 flexib

-0.39

 adults

-0.39

 Flexib

-0.38

 uintptr

-0.38

toxicity

-0.37

flexible

-0.37

DotNetBar

-0.37

 adult

-0.37

Flexible

-0.37

POSITIVE LOGITS

 restore

1.03

 Restore

0.92

 restoration

0.91

 restoring

0.91

restore

0.88

 restored

0.87

 warning

0.84

 restores

0.84

 Restoration

0.84

Restore

0.79

Activations Density 0.080%

instances of the word "restore" and its variations, indicating a focus on recovery or regaining something that has been lost

No Comments

No Known Activations