INDEX

Explanations

terms related to various scientific and technical methodologies, including functions, models, and assays

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Suara

-0.66

ьаж

-0.60

 Мексичка

-0.57

}}}}

-0.55

لكتر

-0.54

 utafitiHapana

-0.53

 zaś

-0.51

 nią

-0.50

anglès

-0.50

Bigr

-0.49

POSITIVE LOGITS

 <<<<<<<<<<<<<<

0.71

IntoConstraints

0.61

BeginContext

0.57

Tikang

0.56

terase

0.55

ciaż

0.55

 uLocal

0.54

AndEndTag

0.53

meris

0.53

DockStyle

0.51

Activations Density 1.912%

terms related to various scientific and technical methodologies, including functions, models, and assays

No Comments

No Known Activations