INDEX

Explanations

phrases that involve complex relationships or concepts within a context

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 typelib

-0.60

ardless

-0.58

PyErr

-0.51

putnik

-0.51

пление

-0.50

 inoltre

-0.50

Mga

-0.49

 élector

-0.48

 sicuramente

-0.47

帖最后由

-0.47

POSITIVE LOGITS

tonode

0.70

Portale

0.66

__':

0.66

Ширина

0.59

didSet

0.58

"):

0.58

ItemBackground

0.57

nemies

0.57

IntoConstraints

0.56

 attaining

0.56

Activations Density 0.245%

phrases that involve complex relationships or concepts within a context

No Comments

No Known Activations