INDEX

Explanations

terms related to "accretion" and its variations in scientific contexts

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

accreted, acculturation, accord

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 FormsModule

-0.51

Pry

-0.48

 While

-0.47

 Gwend

-0.47

while

-0.46

 Merv

-0.46

 createState

-0.44

lf

-0.44

 Siro

-0.44

POSITIVE LOGITS

Acc

0.86

acc

0.85

Acc

0.84

acc

0.84

ACC

0.80

ACC

0.79

 Accu

0.74

 accretion

0.64

accor

0.62

acb

0.59

Activations Density 0.011%

terms related to "accretion" and its variations in scientific contexts

accreted, acculturation, accord

No Comments

No Known Activations