INDEX

Explanations

identifiers and their corresponding attributes in structured data

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

Personendaten

-0.89

 AspNetCore

-0.76

Билгалдахарш

-0.74

المناصب

-0.67

">//

-0.65

 мәкал

-0.65

tagext

-0.64

 ffilmiau

-0.61

WithIOException

-0.59

addGap

-0.58

POSITIVE LOGITS

CppCodeGen

0.65

 LoginComponent

0.62

μως

0.60

grün

0.57

glGen

0.52

 McKnight

0.50

atown

0.49

Czytaj

0.49

 Lindgren

0.49

HideInInspector

0.49

Activations Density 0.687%

identifiers and their corresponding attributes in structured data

No Comments

No Known Activations