INDEX

Explanations

phrases related to potential actions and their consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ParallelGroup

-0.53

 nemlig

-0.48

Demografie

-0.46

балан

-0.46

 compromiso

-0.46

 للمعارف

-0.45

 tenuta

-0.44

<bos>

-0.43

insee

-0.43

 compromisos

-0.42

POSITIVE LOGITS

WireFormatLite

0.66

fjspx

0.63

 '\\;'

0.63

enumii

0.60

sizeCache

0.59

indest

0.58

StoryboardSegue

0.57

 BorderRadius

0.57

もしれません

0.56

XmlAccessType

0.54

Activations Density 0.906%

phrases related to potential actions and their consequences

No Comments

No Known Activations