INDEX

Explanations

common phrases related to analysis and insights within written content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/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.19.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

featureID

-0.72

 lenker

-0.64

offsetof

-0.59

OCCURRED

-0.58

 мәкал

-0.58

Ligações

-0.57

tonode

-0.55

asgi

-0.54

atigable

-0.53

tholes

-0.52

POSITIVE LOGITS

 behalf

0.59

 occasions

0.59

 termes

0.56

URLException

0.56

 nutshell

0.55

 terms

0.55

izarse

0.54

 view

0.52

SequentialGroup

0.51

ChildScrollView

0.49

Activations Density 0.273%

common phrases related to analysis and insights within written content

No Comments

No Known Activations