INDEX

Explanations

scientific terms and jargon related to biological and genomic processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

</i>

-0.55

 Dempsey

-0.54

 Tristan

-0.54

Buffered

-0.53

 sacco

-0.52

mu

-0.51

 Brian

-0.51

Edited

-0.51

gnen

-0.50

Tristan

-0.50

POSITIVE LOGITS

 UIFont

0.92

 يتيمه

0.91

 незавершена

0.89

IntoConstraints

0.87

antaranya

0.80

 Langer

0.80

 lampada

0.80

snmp

0.79

^(@)

0.79

 termica

0.79

Activations Density 7.033%

scientific terms and jargon related to biological and genomic processes

No Comments

No Known Activations