INDEX

Explanations

instances of the word "mention" and its variations indicating references to topics or points within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

SEGUIR

-0.59

不懂

-0.57

 guts

-0.52

 hidup

-0.52

 simpel

-0.50

XMLSchema

-0.50

parker

-0.49

 گیرد

-0.49

 Kamb

-0.49

Ellie

-0.49

POSITIVE LOGITS

 mention

2.89

 Mention

2.78

 mentions

2.65

 mentioning

2.63

Mention

2.58

 mentioned

2.56

mention

2.47

 Mentions

2.38

 Mentioned

2.37

mentioned

2.14

Activations Density 0.084%

instances of the word "mention" and its variations indicating references to topics or points within the text

No Comments

No Known Activations