INDEX

Explanations

references to centrality or positioning within various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 AssemblyCulture

-0.43

 californ

-0.39

 reCAPTCHA

-0.35

 offseason

-0.35

 skor

-0.34

 schuhe

-0.34

 dollari

-0.34

 Eilish

-0.34

IActionResult

-0.33

 formatting

-0.33

POSITIVE LOGITS

 center

1.13

 centre

1.12

 middle

1.07

middle

1.00

 central

0.99

centre

0.98

center

0.96

Middle

0.93

central

0.91

Center

0.91

Activations Density 0.365%

references to centrality or positioning within various contexts

No Comments

No Known Activations