INDEX

Explanations

noun phrases that indicate relationships or connections between entities

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

economic change knee response

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

complexContent

-0.42

PCell

-0.40

 HasFactory

-0.37

grün

-0.37

 usual

-0.37

 sometimes

-0.35

dis

-0.35

 alike

-0.34

 seriousness

-0.34

colgroup

-0.34

POSITIVE LOGITS

MemoryWarning

0.64

parsedMessage

0.58

awtextra

0.57

 ExecuteAsync

0.56

ThemeOverlay

0.55

MessageTagHelper

0.54

principalColumn

0.52

 Autorizaciones

0.51

UserScript

0.51

intios

0.50

Activations Density 0.033%

noun phrases that indicate relationships or connections between entities

economic change knee response

No Comments

No Known Activations