INDEX

Explanations

references to the fit or fitting of items, particularly in relation to sizing

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

fits into

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

 cautions

-0.37

 caution

-0.37

 agent

-0.36

гії

-0.35

ⓧ

-0.35

 agents

-0.35

czyć

-0.34

 actionMode

-0.34

 дії

-0.34

keV

-0.32

POSITIVE LOGITS

Fits

0.63

 fits

0.61

IntoConstraints

0.58

DockStyle

0.58

 rhestr

0.57

ReusableCell

0.56

 CreateTagHelper

0.56

ftagPool

0.56

fitting

0.56

fit

0.55

Activations Density 0.011%

references to the fit or fitting of items, particularly in relation to sizing

fits into

No Comments

No Known Activations