INDEX

Explanations

specific terminology and nomenclature related to technical or scientific classifications and 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

 esternos

-0.42

 kasarigan

-0.40

 Brunner

-0.39

leyebilirsiniz

-0.39

ASR

-0.39

Portale

-0.38

FetchType

-0.38

 ComVisible

-0.38

 Ashraf

-0.38

Pum

-0.37

POSITIVE LOGITS

PD

1.13

fd

1.09

TD

1.09

UD

1.08

VD

1.08

LD

1.08

Kud

1.07

FD

1.06

MD

1.06

WD

1.06

Activations Density 1.711%

specific terminology and nomenclature related to technical or scientific classifications and processes

No Comments

No Known Activations