INDEX

Explanations

words and terms associated with specific scientific studies, particularly in pharmacology and medical research

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

tokens containing prominent “v” letter sequences, often in technical abbreviations and Slavic-style surnames.

oai_token-act-pair · gpt-5 Triggered by @timna

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

er

-1.00

GEBURTSDATUM

-0.72

 gainera

-0.70

ة

-0.66

 isolato

-0.64

 zade

-0.62

 QString

-0.61

ね

-0.61

cher

-0.61

eric

-0.60

POSITIVE LOGITS

fv

1.12

Mev

1.10

WV

1.09

bv

1.08

vv

1.06

MAV

1.05

Dav

1.04

RAV

1.04

DV

1.04

RAV

1.03

Activations Density 0.680%

words and terms associated with specific scientific studies, particularly in pharmacology and medical research

tokens containing prominent “v” letter sequences, often in technical abbreviations and Slavic-style surnames.

No Comments

No Known Activations