INDEX

Explanations

terms related to actions or processes in scientific research

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 nahilalakip

-0.65

 lenker

-0.59

 متعلقه

-0.58

 Мексичка

-0.54

Endless

-0.53

этому

-0.52

 buoyancy

-0.51

ⓧ

-0.51

 חיצוניים

-0.51

Portale

-0.51

POSITIVE LOGITS

in

0.79

by

0.71

BeginContext

0.70

via

0.63

Datuak

0.63

at

0.61

on

0.60

 during

0.59

cheidet

0.58

 bestaan

0.58

Activations Density 0.924%

terms related to actions or processes in scientific research

No Comments

No Known Activations