INDEX

Explanations

import statements in code

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

verwijspagina

-0.68

 ujednoznacz

-0.67

 surla

-0.61

IUrlHelper

-0.55

 resourceCulture

-0.55

 ModelExpression

-0.50

reportWebVitals

-0.49

 мәкал

-0.48

曖昧さ回避

-0.46

DataPropertyName

-0.43

POSITIVE LOGITS

enumii

0.51

ODB

0.46

 views

0.45

urop

0.44

 Kendal

0.44

forts

0.43

clair

0.42

 Boxes

0.42

views

0.42

ruptedException

0.42

Activations Density 0.037%

import statements in code

No Comments

No Known Activations