INDEX

Explanations

references to fixed properties or parameters in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

PerformLayout

-0.95

 Мексичка

-0.94

bolista

-0.93

 <<<<<<<<<<<<<<

-0.90

 שוליים

-0.85

 Coleridge

-0.84

 Biele

-0.84

ItemBackground

-0.83

 Jazeera

-0.83

 productName

-0.81

POSITIVE LOGITS

Fix

1.48

Fix

1.36

fix

1.32

FIX

1.30

fix

1.26

 FIXED

1.21

 Fixed

1.17

 fixes

1.16

Fixed

1.15

 Fixes

1.15

Activations Density 0.055%

references to fixed properties or parameters in a technical context

No Comments

No Known Activations