INDEX

Explanations

occurrences of specific names and organizational terms related to locations and events

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

after specific tokens: to, him, uttered, to,

np_acts-logits-general · gemini-2.0-flash

location-based actions

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

httphttps

-0.52

ScopeManager

-0.51

apimachinery

-0.44

RenderAtEndOf

-0.43

pipeline

-0.42

 SwitchCompat

-0.42

PreExecute

-0.42

autorest

-0.41

 bParam

-0.40

FromNib

-0.40

POSITIVE LOGITS

MessageTagHelper

0.65

enterOuterAlt

0.58

Aktualisiert

0.55

 locaux

0.47

ChrTalk

0.44

 locally

0.43

verwijspagina

0.43

Locally

0.42

irl

0.41

 Locally

0.41

Activations Density 0.776%

occurrences of specific names and organizational terms related to locations and events

after specific tokens: to, him, uttered, to,

location-based actions

No Comments

No Known Activations