INDEX

Explanations

instances of the word "mention" and related forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

parker

-0.70

 recevrez

-0.68

 guts

-0.64

STL

-0.64

 Kamil

-0.60

 alá

-0.60

 StatefulWidget

-0.59

Ellie

-0.59

dshaw

-0.56

Respectfully

-0.55

POSITIVE LOGITS

 Mention

1.65

 mentions

1.62

 mention

1.58

Mention

1.58

 Mentions

1.58

 mentioning

1.55

mention

1.45

 Mentioned

1.42

 mentioned

1.41

mentions

1.35

Activations Density 0.066%

instances of the word "mention" and related forms

No Comments

No Known Activations