INDEX

Explanations

references to researchers and studies

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

 when

-0.56

DockStyle

-0.55

DotNetBar

-0.54

tagHelper

-0.54

sidemargin

-0.52

 once

-0.49

when

-0.48

Cuándo

-0.47

yecek

-0.46

RSpec

-0.46

POSITIVE LOGITS

RUNNING

0.58

 Running

0.54

GEBURTSDATUM

0.51

jfree

0.50

 khuyến

0.50

Running

0.49

rungsseite

0.49

 <>",

0.49

IUrlHelper

0.49

oustics

0.49

Activations Density 0.188%

references to researchers and studies

No Comments

No Known Activations