INDEX

Explanations

terms related to data processing and analysis in various contexts

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

Preceding words of "vehicle", "genes", "regions", or "signals"

np_acts-logits-general · gemini-2.0-flash

paint vehicle, lifting apparatus, consumer panel

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

AddTagHelper

-0.89

IndentedString

-0.81

WebVitals

-0.78

 CreateTagHelper

-0.77

 Wikimedijinoj

-0.77

 Chwiliwch

-0.75

findpost

-0.75

<unused8>

-0.74

<unused41>

-0.73

[@BOS@]

-0.73

POSITIVE LOGITS

<eos>

0.50

0.28

 âgées

0.28

 tranquille

0.27

ạp

0.26

ånd

0.25

ライド

0.25

 acus

0.25

↵

0.24

hay

0.24

Activations Density 0.337%

terms related to data processing and analysis in various contexts

Preceding words of "vehicle", "genes", "regions", or "signals"

paint vehicle, lifting apparatus, consumer panel

No Comments

No Known Activations