INDEX

Explanations

references to people or populations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Normdatei

-0.60

Complete

-0.59

 complete

-0.58

 Complete

-0.57

Demografía

-0.54

NOPQRST

-0.54

 Metab

-0.53

complete

-0.51

CompleteListener

-0.51

 Roskov

-0.51

POSITIVE LOGITS

haps

0.58

opel

0.57

0.54

formance

0.53

 EconPapers

0.52

BagConstraints

0.52

########.

0.50

 broadest

0.49

SourceChecksum

0.48

 ople

0.47

Activations Density 0.180%

references to people or populations

No Comments

No Known Activations