INDEX

Explanations

function-related terms and actions associated with coding or programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rboles

-0.78

rvore

-0.72

parsedMessage

-0.70

 GreatSchools

-0.67

Isra

-0.64

protoimpl

-0.63

bersicht

-0.62

esterday

-0.61

ueuse

-0.60

basicConfig

-0.60

POSITIVE LOGITS

 ולה

0.78

lizar

0.70

 Harwood

0.69

decer

0.67

 etmek

0.66

quisar

0.65

er

0.64

ricular

0.64

 Lewin

0.64

 Harlow

0.64

Activations Density 0.062%

function-related terms and actions associated with coding or programming

No Comments

No Known Activations