INDEX

Explanations

programming-related terms and keywords associated with data handling and processing

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

pyl

-0.67

pylene

-0.65

ahnya

-0.58

vician

-0.57

onema

-0.56

ricular

-0.56

 alia

-0.54

PerformLayout

-0.53

Jo

-0.53

NewLabel

-0.53

POSITIVE LOGITS

ⓧ

1.05

 Theſe

1.04

 Monfieur

0.96

 Diſ

0.93

Efq

0.89

 Chriſt

0.88

 Majefty

0.87

 Perſ

0.86

 ſeveral

0.86

 myſelf

0.85

Activations Density 1.068%

programming-related terms and keywords associated with data handling and processing

No Comments

No Known Activations