INDEX

Explanations

terms related to connectors and plugins

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

Popup window

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 marshal

-0.35

 immagin

-0.32

IGENCE

-0.31

FULLY

-0.31

 somebody

-0.30

 fully

-0.29

 constable

-0.29

 Fully

-0.28

IG

-0.28

titleMargin

-0.28

POSITIVE LOGITS

Throwaway

0.61

flashdata

0.61

parsedMessage

0.60

 transfieras

0.57

providedIn

0.57

 QtWidgets

0.56

 requestCode

0.55

addCriterion

0.55

HttpDelete

0.55

 onPostExecute

0.54

Activations Density 0.134%

terms related to connectors and plugins

Popup window

No Comments

No Known Activations