INDEX

Explanations

expressions of personal experiences and interactions

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

this item/model

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

这些人

-0.70

 Taktlose

-0.68

這些

-0.63

 amelyek

-0.63

 onları

-0.63

 snippetHide

-0.62

ViewFeatures

-0.59

Chham

-0.59

 AssemblyTitle

-0.58

 disambiguazione

-0.58

POSITIVE LOGITS

这款

0.64

 chiếc

0.60

這款

0.53

该

0.49

該

0.48

这只

0.47

 sebuah

0.42

 crafted

0.41

该

0.40

THE

0.40

Activations Density 0.070%

expressions of personal experiences and interactions

this item/model

No Comments

No Known Activations