INDEX

Explanations

various forms of the word "mention" and its related context in texts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

parker

-0.63

Wal

-0.59

owa

-0.57

不懂

-0.56

Wy

-0.54

Wal

-0.54

 guts

-0.53

 Kamil

-0.51

 Parr

-0.51

 Gwyn

-0.50

POSITIVE LOGITS

 Mention

2.25

 mention

2.23

 mentions

2.17

 mentioning

2.17

Mention

2.10

 Mentions

2.03

mention

2.02

 mentioned

1.99

 Mentioned

1.90

mentions

1.71

Activations Density 0.056%

various forms of the word "mention" and its related context in texts

No Comments

No Known Activations