INDEX

Explanations

names of authors and contributors related to scholarly work or research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 Waco

-0.66

bonnet

-0.55

genic

-0.55

 Gujarati

-0.54

 TEXAS

-0.53

 Texas

-0.53

 Gujarat

-0.53

 Nigerian

-0.52

 Saginaw

-0.52

 Dallas

-0.52

POSITIVE LOGITS

 Bulgarian

1.22

 Bulgaria

1.20

Bulgaria

1.05

 Sofia

1.01

Bulg

0.99

Sofia

0.87

 Bulg

0.82

 Bulgar

0.79

OGND

0.74

 Telerik

0.74

Activations Density 0.051%

names of authors and contributors related to scholarly work or research

No Comments

No Known Activations