INDEX

Explanations

expressions indicating active participation or involvement in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 Brito

-0.69

 sodass

-0.67

く

-0.66

edas

-0.65

GOTREF

-0.64

 Dumont

-0.63

 dass

-0.63

 Cruz

-0.63

ers

-0.62

POSITIVE LOGITS

 involved

1.72

 Involved

1.69

involved

1.62

 involve

1.59

 INVOL

1.50

 involves

1.49

 involving

1.48

 involvement

1.48

 INVOLVED

1.47

 Involvement

1.46

Activations Density 0.087%

expressions indicating active participation or involvement in various contexts

No Comments

No Known Activations