INDEX

Explanations

concepts related to feature selection and data processing techniques in research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 rhestr

-0.73

ArrowToggle

-0.63

rensa

-0.61

GraphicsUnit

-0.59

 setuptools

-0.58

 bağlantılar

-0.56

 OMITBAD

-0.55

MLLoader

-0.55

Chham

-0.55

tonode

-0.54

POSITIVE LOGITS

 proposed

0.69

 Fuzzy

0.68

 financières

0.64

 fuzzy

0.63

Fuzzy

0.63

 Proposed

0.63

 návr

0.62

 MATLAB

0.62

 biodiesel

0.62

 proposées

0.62

Activations Density 0.716%

concepts related to feature selection and data processing techniques in research

No Comments

No Known Activations