INDEX

Explanations

programming and computational terminology related to experiments and functions

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

experiments or mathematical symbols

np_acts-logits-general · gemini-2.0-flash

proposed, designed, or shown experiments

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 brands

-0.35

QPalette

-0.34

 brand

-0.34

 Мексичка

-0.33

 stocks

-0.32

优势

-0.32

 laurels

-0.32

Bakgrunnsstoff

-0.32

Demografía

-0.31

 estudantes

-0.31

POSITIVE LOGITS

 ProtoMessage

0.58

RenderAtEndOf

0.58

BASEPATH

0.56

المناصب

0.52

 experiments

0.52

Vidite

0.52

 Experiments

0.52

 MainAxisSize

0.51

 simplifié

0.51

Література

0.50

Activations Density 2.130%

programming and computational terminology related to experiments and functions

experiments or mathematical symbols

proposed, designed, or shown experiments

No Comments

No Known Activations