INDEX

Explanations

mathematical notation and symbols typically used in formal proofs or equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 otomatig

-1.01

 beginnetje

-0.96

 referenties

-0.90

verwijspagina

-0.89

 autorytatywna

-0.86

LookAnd

-0.84

oredCriteria

-0.82

AccessorTable

-0.81

 ligiloj

-0.80

 propOrder

-0.80

POSITIVE LOGITS

{~

1.02

mathrm

0.73

โ

0.68

0.64

[toxicity=0]

0.59

 Rams

0.58

 dibuka

0.57

евич

0.56

enumi

0.56

Activations Density 0.025%

mathematical notation and symbols typically used in formal proofs or equations

No Comments

No Known Activations