INDEX

Explanations

programming-related keywords and function calls

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/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.15.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

ESTAMP

-0.52

 InputDecoration

-0.50

onAttach

-0.49

 Weise

-0.47

orto

-0.46

 AttributeSet

-0.46

жом

-0.45

cookieParser

-0.45

ospel

-0.44

IsInitialized

-0.44

POSITIVE LOGITS

Gön

0.60

 XCTest

0.60

Tym

0.56

 autorytatywna

0.55

boden

0.55

oflavin

0.55

 localVar

0.55

ametri

0.55

发表于

0.54

 استنادى

0.53

Activations Density 0.136%

programming-related keywords and function calls

No Comments

No Known Activations