INDEX

Explanations

references to examination, analysis, or evaluation processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

oredCriteria

-0.75

qrstuvwxyz

-0.50

 bienvenue

-0.48

 réus

-0.47

ocimiento

-0.46

GEBURTSDATUM

-0.45

chauss

-0.45

Permanent

-0.44

 Throwable

-0.44

Jvm

-0.43

POSITIVE LOGITS

 thoroughly

1.21

 carefully

1.17

 closely

1.16

 exhaus

0.95

 intensively

0.95

 intently

0.95

caref

0.94

 extensively

0.90

 cuidadosamente

0.87

 further

0.86

Activations Density 0.602%

references to examination, analysis, or evaluation processes

No Comments

No Known Activations