INDEX

Explanations

instances of articles and determiners related to people or roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

牢

-0.55

 itemView

-0.54

edly

-0.52

lijks

-0.52

experiments

-0.48

gehenden

-0.48

น์

-0.48

torta

-0.48

ographs

-0.47

 Once

-0.47

POSITIVE LOGITS

KURZBESCHREIBUNG

0.78

 snippetHide

0.78

EndContext

0.76

Bioaccumulative

0.72

 GetEnumerator

0.72

tvguidetime

0.70

новништво

0.70

GraphicsUnit

0.69

 contextLoads

0.69

interopRequire

0.68

Activations Density 0.669%

instances of articles and determiners related to people or roles

No Comments

No Known Activations