INDEX

Explanations

references to "U" along with associated metrics and identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 ExecuteAsync

-0.79

 AssemblyCulture

-0.68

 doInBackground

-0.67

CrossRef

-0.65

RefNanny

-0.59

SuppressLint

-0.59

WebpackPlugin

-0.58

IBar

-0.58

fjspx

-0.58

/\.

-0.56

POSITIVE LOGITS

 uVar

0.74

uj

0.70

uu

0.69

UU

0.69

 UserController

0.67

 Urqu

0.66

Ull

0.65

UIS

0.64

 uncin

0.64

0.63

Activations Density 0.899%

references to "U" along with associated metrics and identifiers

No Comments

No Known Activations